Surya Nepal

Chandra Thapa, Seung Ick Jang, Muhammad Ejaz Ahmed et al.

The large transformer-based language models demonstrate excellent performance in natural language processing. By considering the transferability of the knowledge gained by these models in one domain to other related domains, and the closeness of natural languages to high-level programming languages, such as C/C++, this work studies how to leverage (large) transformer-based language models in detecting software vulnerabilities and how good are these models for vulnerability detection tasks. In this regard, firstly, a systematic (cohesive) framework that details source code translation, model preparation, and inference is presented. Then, an empirical analysis is performed with software vulnerability datasets with C/C++ source codes having multiple vulnerabilities corresponding to the library function call, pointer usage, array usage, and arithmetic expression. Our empirical results demonstrate the good performance of the language models in vulnerability detection. Moreover, these language models have better performance metrics, such as F1-score, than the contemporary models, namely bidirectional long short-term memory and bidirectional gated recurrent unit. Experimenting with the language models is always challenging due to the requirement of computing resources, platforms, libraries, and dependencies. Thus, this paper also analyses the popular platforms to efficiently fine-tune these models and present recommendations while choosing the platforms.

David D. Nguyen, Surya Nepal, Salil S. Kanhere

Designing visually appealing layouts for multimedia documents containing text, graphs and images requires a form of creative intelligence. Modelling the generation of layouts has recently gained attention due to its importance in aesthetics and communication style. In contrast to standard prediction tasks, there are a range of acceptable layouts which depend on user preferences. For example, a poster designer may prefer logos on the top-left while another prefers logos on the bottom-right. Both are correct choices yet existing machine learning models treat layouts as a single choice prediction problem. In such situations, these models would simply average over all possible choices given the same input forming a degenerate sample. In the above example, this would form an unacceptable layout with a logo in the centre. In this paper, we present an auto-regressive neural network architecture, called LayoutMCL, that uses multi-choice prediction and winner-takes-all loss to effectively stabilise layout generation. LayoutMCL avoids the averaging problem by using multiple predictors to learn a range of possible options for each layout object. This enables LayoutMCL to generate multiple and diverse layouts from a single input which is in contrast with existing approaches which yield similar layouts with minor variations. Through quantitative benchmarks on real data (magazine, document and mobile app layouts), we demonstrate that LayoutMCL reduces Fréchet Inception Distance (FID) by 83-98% and generates significantly more diversity in comparison to existing approaches.

Shuo Wang, Sharif Abuadbba, Sidharth Agarwal et al.

Existing integrity verification approaches for deep models are designed for private verification (i.e., assuming the service provider is honest, with white-box access to model parameters). However, private verification approaches do not allow model users to verify the model at run-time. Instead, they must trust the service provider, who may tamper with the verification results. In contrast, a public verification approach that considers the possibility of dishonest service providers can benefit a wider range of users. In this paper, we propose PublicCheck, a practical public integrity verification solution for services of run-time deep models. PublicCheck considers dishonest service providers, and overcomes public verification challenges of being lightweight, providing anti-counterfeiting protection, and having fingerprinting samples that appear smooth. To capture and fingerprint the inherent prediction behaviors of a run-time model, PublicCheck generates smoothly transformed and augmented encysted samples that are enclosed around the model's decision boundary while ensuring that the verification queries are indistinguishable from normal queries. PublicCheck is also applicable when knowledge of the target model is limited (e.g., with no knowledge of gradients or model parameters). A thorough evaluation of PublicCheck demonstrates the strong capability for model integrity breach detection (100% detection accuracy with less than 10 black-box API queries) against various model integrity attacks and model compression attacks. PublicCheck also demonstrates the smooth appearance, feasibility, and efficiency of generating a plethora of encysted samples for fingerprinting.

Alsharif Abuadbba, Shuo Wang, Mahathir Almashor et al.

Web phishing remains a serious cyber threat responsible for most data breaches. Machine Learning (ML)-based anti-phishing detectors are seen as an effective countermeasure, and are increasingly adopted by web-browsers and software products. However, with an average of 10K phishing links reported per hour to platforms such as PhishTank and VirusTotal (VT), the deficiencies of such ML-based solutions are laid bare. We first explore how phishing sites bypass ML-based detection with a deep dive into 13K phishing pages targeting major brands such as Facebook. Results show successful evasion is caused by: (1) use of benign services to obscure phishing URLs; (2) high similarity between the HTML structures of phishing and benign pages; (3) hiding the ultimate phishing content within Javascript and running such scripts only on the client; (4) looking beyond typical credentials and credit cards for new content such as IDs and documents; (5) hiding phishing content until after human interaction. We attribute the root cause to the dependency of ML-based models on the vertical feature space (webpage content). These solutions rely only on what phishers present within the page itself. Thus, we propose Anti-SubtlePhish, a more resilient model based on logistic regression. The key augmentation is the inclusion of a horizontal feature space, which examines correlation variables between the final render of suspicious pages against what trusted services have recorded (e.g., PageRank). To defeat (1) and (2), we correlate information between WHOIS, PageRank, and page analytics. To combat (3), (4) and (5), we correlate features after rendering the page. Experiments with 100K phishing/benign sites show promising accuracy (98.8%). We also obtained 100% accuracy against 0-day phishing pages that were manually crafted, comparing well to the 0% recorded by VT vendors over the first four days.

David Liebowitz, Surya Nepal, Kristen Moore et al.

Deception is rapidly growing as an important tool for cyber defence, complementing existing perimeter security measures to rapidly detect breaches and data theft. One of the factors limiting the use of deception has been the cost of generating realistic artefacts by hand. Recent advances in Machine Learning have, however, created opportunities for scalable, automated generation of realistic deceptions. This vision paper describes the opportunities and challenges involved in developing models to mimic many common elements of the IT stack for deception effects.

Roelien C. Timmer, David Liebowitz, Surya Nepal et al.

Each and every organisation releases information in a variety of forms ranging from annual reports to legal proceedings. Such documents may contain sensitive information and releasing them openly may lead to the leakage of confidential information. Detection of sentences that contain sensitive information in documents can help organisations prevent the leakage of valuable confidential information. This is especially challenging when such sentences contain a substantial amount of information or are paraphrased versions of known sensitive content. Current approaches to sensitive information detection in such complex settings are based on keyword-based approaches or standard machine learning models. In this paper, we wish to explore whether pre-trained transformer models are well suited to detect complex sensitive information. Pre-trained transformers are typically trained on an enormous amount of text and therefore readily learn grammar, structure and other linguistic features, making them particularly attractive for this task. Through our experiments on the Monsanto trial data set, we observe that the fine-tuned Bidirectional Encoder Representations from Transformers (BERT) transformer model performs better than traditional models. We experimented with four different categories of documents in the Monsanto dataset and observed that BERT achieves better F2 scores by 24.13\% to 65.79\% for GHOST, 30.14\% to 54.88\% for TOXIC, 39.22\% for CHEMI, 53.57\% for REGUL compared to existing sensitive information detection models.

Roelien C. Timmer, David Liebowitz, Surya Nepal et al.

Honeyfile deployment is a useful breach detection method in cyber deception that can also inform defenders about the intent and interests of intruders and malicious insiders. A key property of a honeyfile, enticement, is the extent to which the file can attract an intruder to interact with it. We introduce a novel metric, Topic Semantic Matching (TSM), which uses topic modelling to represent files in the repository and semantic matching in an embedding vector space to compare honeyfile text and topic words robustly. We also present a honeyfile corpus created with different Natural Language Processing (NLP) methods. Experiments show that TSM is effective in inter-corpus comparisons and is a promising tool to measure the enticement of honeyfiles. TSM is the first measure to use NLP techniques to quantify the enticement of honeyfile content that compares the essential topical content of local contexts to honeyfiles and is robust to paraphrasing.

Huihui Gong, Minjing Dong, Siqi Ma et al.

Deep neural networks (DNNs) have achieved state-of-the-art performance on face recognition (FR) tasks in the last decade. In real scenarios, the deployment of DNNs requires taking various face accessories into consideration, like glasses, hats, and masks. In the COVID-19 pandemic era, wearing face masks is one of the most effective ways to defend against the novel coronavirus. However, DNNs are known to be vulnerable to adversarial examples with a small but elaborated perturbation. Thus, a facial mask with adversarial perturbations may pose a great threat to the widely used deep learning-based FR models. In this paper, we consider a challenging adversarial setting: targeted attack against FR models. We propose a new stealthy physical masked FR attack via adversarial style optimization. Specifically, we train an adversarial style mask generator that hides adversarial perturbations inside style masks. Moreover, to ameliorate the phenomenon of sub-optimization with one fixed style, we propose to discover the optimal style given a target through style optimization in a continuous relaxation manner. We simultaneously optimize the generator and the style selection for generating strong and stealthy adversarial style masks. We evaluated the effectiveness and transferability of our proposed method via extensive white-box and black-box digital experiments. Furthermore, we also conducted physical attack experiments against local FR models and online platforms.

Iqbal H. Sarker, Helge Janicke, Nazeeruddin Mohammad et al.

This position paper explores the broad landscape of AI potentiality in the context of cybersecurity, with a particular emphasis on its possible risk factors with awareness, which can be managed by incorporating human experts in the loop, i.e., "Human-AI" teaming. As artificial intelligence (AI) technologies advance, they will provide unparalleled opportunities for attack identification, incident response, and recovery. However, the successful deployment of AI into cybersecurity measures necessitates an in-depth understanding of its capabilities, challenges, and ethical and legal implications to handle associated risk factors in real-world application areas. Towards this, we emphasize the importance of a balanced approach that incorporates AI's computational power with human expertise. AI systems may proactively discover vulnerabilities and detect anomalies through pattern recognition, and predictive modeling, significantly enhancing speed and accuracy. Human experts can explain AI-generated decisions to stakeholders, regulators, and end-users in critical situations, ensuring responsibility and accountability, which helps establish trust in AI-driven security solutions. Therefore, in this position paper, we argue that human-AI teaming is worthwhile in cybersecurity, in which human expertise such as intuition, critical thinking, or contextual understanding is combined with AI's computational power to improve overall cyber defenses.

Hua Ma, Shang Wang, Yansong Gao et al.

All current backdoor attacks on deep learning (DL) models fall under the category of a vertical class backdoor (VCB) -- class-dependent. In VCB attacks, any sample from a class activates the implanted backdoor when the secret trigger is present. Existing defense strategies overwhelmingly focus on countering VCB attacks, especially those that are source-class-agnostic. This narrow focus neglects the potential threat of other simpler yet general backdoor types, leading to false security implications. This study introduces a new, simple, and general type of backdoor attack coined as the horizontal class backdoor (HCB) that trivially breaches the class dependence characteristic of the VCB, bringing a fresh perspective to the community. HCB is now activated when the trigger is presented together with an innocuous feature, regardless of class. For example, the facial recognition model misclassifies a person who wears sunglasses with a smiling innocuous feature into the targeted person, such as an administrator, regardless of which person. The key is that these innocuous features are horizontally shared among classes but are only exhibited by partial samples per class. Extensive experiments on attacking performance across various tasks, including MNIST, facial recognition, traffic sign recognition, object detection, and medical diagnosis, confirm the high efficiency and effectiveness of the HCB. We rigorously evaluated the evasiveness of the HCB against a series of eleven representative countermeasures, including Fine-Pruning (RAID 18'), STRIP (ACSAC 19'), Neural Cleanse (Oakland 19'), ABS (CCS 19'), Februus (ACSAC 20'), NAD (ICLR 21'), MNTD (Oakland 21'), SCAn (USENIX SEC 21'), MOTH (Oakland 22'), Beatrix (NDSS 23'), and MM-BD (Oakland 24'). None of these countermeasures prove robustness, even when employing a simplistic trigger, such as a small and static white-square patch.

David D. Nguyen, David Leibowitz, Surya Nepal et al.

Generative models with discrete latent representations have recently demonstrated an impressive ability to learn complex high-dimensional data distributions. However, their performance relies on a long sequence of tokens per instance and a large number of codebook entries, resulting in long sampling times and considerable computation to fit the categorical posterior. To address these issues, we propose the Masked Vector Quantization (MVQ) framework which increases the representational capacity of each code vector by learning mask configurations via a stochastic winner-takes-all training regime called Multiple Hypothese Dropout (MH-Dropout). On ImageNet 64$\times$64, MVQ reduces FID in existing vector quantization architectures by up to $68\%$ at 2 tokens per instance and $57\%$ at 5 tokens. These improvements widen as codebook entries is reduced and allows for $7\textit{--}45\times$ speed-up in token sampling during inference. As an additional benefit, we find that smaller latent spaces lead to MVQ identifying transferable visual representations where multiple can be smoothly combined.

Huihui Gong, Minjing Dong, Siqi Ma et al.

Adversarial training serves as one of the most popular and effective methods to defend against adversarial perturbations. However, most defense mechanisms only consider a single type of perturbation while various attack methods might be adopted to perform stronger adversarial attacks against the deployed model in real-world scenarios, e.g., $\ell_2$ or $\ell_\infty$. Defending against various attacks can be a challenging problem since multi-perturbation adversarial training and its variants only achieve suboptimal robustness trade-offs, due to the theoretical limit to multi-perturbation robustness for a single model. Besides, it is impractical to deploy large models in some storage-efficient scenarios. To settle down these drawbacks, in this paper we propose a novel multi-perturbation adversarial training framework, parameter-saving adversarial training (PSAT), to reinforce multi-perturbation robustness with an advantageous side effect of saving parameters, which leverages hypernetworks to train specialized models against a single perturbation and aggregate these specialized models to defend against multiple perturbations. Eventually, we extensively evaluate and compare our proposed method with state-of-the-art single/multi-perturbation robust methods against various latest attack methods on different datasets, showing the robustness superiority and parameter efficiency of our proposed method, e.g., for the CIFAR-10 dataset with ResNet-50 as the backbone, PSAT saves approximately 80\% of parameters with achieving the state-of-the-art robustness trade-off accuracy.

Seonhye Park, Alsharif Abuadbba, Shuo Wang et al.

Training deep neural networks (DNNs) requires large datasets and powerful computing resources, which has led some owners to restrict redistribution without permission. Watermarking techniques that embed confidential data into DNNs have been used to protect ownership, but these can degrade model performance and are vulnerable to watermark removal attacks. Recently, DeepJudge was introduced as an alternative approach to measuring the similarity between a suspect and a victim model. While DeepJudge shows promise in addressing the shortcomings of watermarking, it primarily addresses situations where the suspect model copies the victim's architecture. In this study, we introduce DeepTaster, a novel DNN fingerprinting technique, to address scenarios where a victim's data is unlawfully used to build a suspect model. DeepTaster can effectively identify such DNN model theft attacks, even when the suspect model's architecture deviates from the victim's. To accomplish this, DeepTaster generates adversarial images with perturbations, transforms them into the Fourier frequency domain, and uses these transformed images to identify the dataset used in a suspect model. The underlying premise is that adversarial images can capture the unique characteristics of DNNs built with a specific dataset. To demonstrate the effectiveness of DeepTaster, we evaluated the effectiveness of DeepTaster by assessing its detection accuracy on three datasets (CIFAR10, MNIST, and Tiny-ImageNet) across three model architectures (ResNet18, VGG16, and DenseNet161). We conducted experiments under various attack scenarios, including transfer learning, pruning, fine-tuning, and data augmentation. Specifically, in the Multi-Architecture Attack scenario, DeepTaster was able to identify all the stolen cases across all datasets, while DeepJudge failed to detect any of the cases.

Mariya Shmalko, Alsharif Abuadbba, Raj Gaire et al.

Email phishing has become more prevalent and grows more sophisticated over time. To combat this rise, many machine learning (ML) algorithms for detecting phishing emails have been developed. However, due to the limited email data sets on which these algorithms train, they are not adept at recognising varied attacks and, thus, suffer from concept drift; attackers can introduce small changes in the statistical characteristics of their emails or websites to successfully bypass detection. Over time, a gap develops between the reported accuracy from literature and the algorithm's actual effectiveness in the real world. This realises itself in frequent false positive and false negative classifications. To this end, we propose a multidimensional risk assessment of emails to reduce the feasibility of an attacker adapting their email and avoiding detection. This horizontal approach to email phishing detection profiles an incoming email on its main features. We develop a risk assessment framework that includes three models which analyse an email's (1) threat level, (2) cognitive manipulation, and (3) email type, which we combine to return the final risk assessment score. The Profiler does not require large data sets to train on to be effective and its analysis of varied email features reduces the impact of concept drift. Our Profiler can be used in conjunction with ML approaches, to reduce their misclassifications or as a labeller for large email data sets in the training stage. We evaluate the efficacy of the Profiler against a machine learning ensemble using state-of-the-art ML algorithms on a data set of 9000 legitimate and 900 phishing emails from a large Australian research organisation. Our results indicate that the Profiler's mitigates the impact of concept drift, and delivers 30% less false positive and 25% less false negative email classifications over the ML ensemble's approach.

Jiajun Huang, Xinqi Zhu, Chengbin Du et al.

Forgery facial images and videos have increased the concern of digital security. It leads to the significant development of detecting forgery data recently. However, the data, especially the videos published on the Internet, are usually compressed with lossy compression algorithms such as H.264. The compressed data could significantly degrade the performance of recent detection algorithms. The existing anti-compression algorithms focus on enhancing the performance in detecting heavily compressed data but less consider the compression adaption to the data from various compression levels. We believe creating a forgery detection model that can handle the data compressed with unknown levels is important. To enhance the performance for such models, we consider the weak compressed and strong compressed data as two views of the original data and they should have similar representation and relationships with other samples. We propose a novel anti-compression forgery detection framework by maintaining closer relations within data under different compression levels. Specifically, the algorithm measures the pair-wise similarity within data as the relations, and forcing the relations of weak and strong compressed data close to each other, thus improving the discriminate power for detecting strong compressed data. To achieve a better strong compressed data relation guided by the less compressed one, we apply video level contrastive learning for weak compressed data, which forces the model to produce similar representations within the same video and far from the negative samples. The experiment results show that the proposed algorithm could boost performance for strong compressed data while improving the accuracy rate when detecting the clean data.

Minhui Xue, Surya Nepal, Ling Liu et al.

This paper plans to develop an Equitable and Responsible AI framework with enabling techniques and algorithms for the Internet of Energy (IoE), in short, RAI4IoE. The energy sector is going through substantial changes fueled by two key drivers: building a zero-carbon energy sector and the digital transformation of the energy infrastructure. We expect to see the convergence of these two drivers resulting in the IoE, where renewable distributed energy resources (DERs), such as electric cars, storage batteries, wind turbines and photovoltaics (PV), can be connected and integrated for reliable energy distribution by leveraging advanced 5G-6G networks and AI technology. This allows DER owners as prosumers to participate in the energy market and derive economic incentives. DERs are inherently asset-driven and face equitable challenges (i.e., fair, diverse and inclusive). Without equitable access, privileged individuals, groups and organizations can participate and benefit at the cost of disadvantaged groups. The real-time management of DER resources not only brings out the equity problem to the IoE, it also collects highly sensitive location, time, activity dependent data, which requires to be handled responsibly (e.g., privacy, security and safety), for AI-enhanced predictions, optimization and prioritization services, and automated management of flexible resources. The vision of our project is to ensure equitable participation of the community members and responsible use of their data in IoE so that it could reap the benefits of advances in AI to provide safe, reliable and sustainable energy services.

Alsharif Abuadbba, Nazatul Sultan, Surya Nepal et al.

AI is moving from domain-specific autonomy in closed, predictable settings to large-language-model-driven agents that plan and act in open, cross-organizational environments. As a result, the cybersecurity risk landscape is changing in fundamental ways. Agentic AI systems can plan, act, collaborate, and persist over time, functioning as participants in complex socio-technical ecosystems rather than as isolated software components. Although recent work has strengthened defenses against model and pipeline level vulnerabilities such as prompt injection, data poisoning, and tool misuse, these system centric approaches may fail to capture risks that arise from autonomy, interaction, and emergent behavior. This article introduces the 4C Framework for multi-agent AI security, inspired by societal governance. It organizes agentic risks across four interdependent dimensions: Core (system, infrastructure, and environmental integrity), Connection (communication, coordination, and trust), Cognition (belief, goal, and reasoning integrity), and Compliance (ethical, legal, and institutional governance). By shifting AI security from a narrow focus on system-centric protection to the broader preservation of behavioral integrity and intent, the framework complements existing AI security strategies and offers a principled foundation for building agentic AI systems that are trustworthy, governable, and aligned with human values.

Chuyang Zhou, Jiajun Huang, Daochang Liu et al.

Facial forgery detection is a crucial but extremely challenging topic, with the fast development of forgery techniques making the synthetic artefact highly indistinguishable. Prior works show that by mining both spatial and frequency information the forgery detection performance of deep learning models can be vastly improved. However, leveraging multiple types of information usually requires more than one branch in the neural network, which makes the model heavy and cumbersome. Knowledge distillation, as an important technique for efficient modelling, could be a possible remedy. We find that existing knowledge distillation methods have difficulties distilling a dual-branch model into a single-branch model. More specifically, knowledge distillation on both the spatial and frequency branches has degraded performance than distillation only on the spatial branch. To handle such problem, we propose a novel two-in-one knowledge distillation framework which can smoothly merge the information from a large dual-branch network into a small single-branch network, with the help of different dedicated feature projectors and the gradient homogenization technique. Experimental analysis on two datasets, FaceForensics++ and Celeb-DF, shows that our proposed framework achieves superior performance for facial forgery detection with much fewer parameters.

Bushra Sabir, Shigang Liu, Seung Ick Jang et al.

Automatically generating source code from natural language using large language models (LLMs) is becoming common, yet security vulnerabilities persist despite advances in fine tuning and prompting. In this work, we systematically evaluate whether multi LLM ensembles and collaborative strategies can meaningfully improve secure code generation. We present MULTI-LLMSECCODEEVAL, a framework for assessing and enhancing security across the vulnerability management lifecycle by combining multiple LLMs with static analysis and structured collaboration. Using SecLLMEval and SecLLMHolmes, we benchmark ten pipelines spanning single model, ensemble, collaborative, and hybrid designs. Our results show that ensemble pipelines augmented with static analysis improve secure code generation over single LLM baselines by up to 47.3% on SecLLMEval and 19.3% on SecLLMHolmes, while purely LLM based collaborative pipelines yield smaller gains of 8.9% to 22.3%. Hybrid pipelines that integrate ensembling, detection, and patching achieve the strongest security performance, outperforming the best ensemble baseline by 1.78% to 4.72% and collaborative baselines by 19.81% to 26.78%. Ablation studies reveal that model scale alone does not ensure security. Smaller, structured multi model ensembles consistently outperform large monolithic LLMs. Overall, our findings demonstrate that secure code does not emerge from scale, but from carefully orchestrated multi model system design.

Hassan Ali, Surya Nepal, Salil S. Kanhere et al.

Recent works have shown that Federated Learning (FL) is vulnerable to backdoor attacks. Existing defenses cluster submitted updates from clients and select the best cluster for aggregation. However, they often rely on unrealistic assumptions regarding client submissions and sampled clients population while choosing the best cluster. We show that in realistic FL settings, state-of-the-art (SOTA) defenses struggle to perform well against backdoor attacks in FL. To address this, we highlight that backdoored submissions are adversarially biased and overconfident compared to clean submissions. We, therefore, propose an Adversarially Guided Stateful Defense (AGSD) against backdoor attacks on Deep Neural Networks (DNNs) in FL scenarios. AGSD employs adversarial perturbations to a small held-out dataset to compute a novel metric, called the trust index, that guides the cluster selection without relying on any unrealistic assumptions regarding client submissions. Moreover, AGSD maintains a trust state history of each client that adaptively penalizes backdoored clients and rewards clean clients. In realistic FL settings, where SOTA defenses mostly fail to resist attacks, AGSD mostly outperforms all SOTA defenses with minimal drop in clean accuracy (5% in the worst-case compared to best accuracy) even when (a) given a very small held-out dataset -- typically AGSD assumes 50 samples (<= 0.1% of the training data) and (b) no heldout dataset is available, and out-of-distribution data is used instead. For reproducibility, our code will be openly available at: https://github.com/hassanalikhatim/AGSD.

David Holmes, Ahmad Moshin, Surya Nepal et al.

Existing Digital Twin (DT) approaches often lack semantic reasoning capabilities for effective cybersecurity modelling in Cyber-Physical Systems (CPS). This paper presents HySecTwin, a knowledge-driven digital twin architecture that places automated reasoning at the core of real-time threat detection. HySecTwin incorporates semantic modelling to transform heterogeneous CPS telemetry, device attributes, and operational relationships into machine-interpretable representations, combined with an embedded reasoning engine operating over contextualized system states. Unlike opaque detection methods, the framework integrates deterministic rule-based inference with hybrid fuzzy reasoning to generate explicit, interpretable, and auditable security assessments from live device telemetry. This enables context-aware monitoring of complex CPS environments while preserving transparency and trust. Experimental evaluation using a representative CPS testbed and MITRE ATT\&CK campaign-inspired attack scenarios demonstrates sub-millisecond twin synchronization latency and up to 21.5\% faster threat detection compared with deterministic reasoning alone. The results show that semantic modelling, semantic enrichment, and hybrid reasoning improve explainability and resilience without extra system overhead. HySecTwin provides a lightweight, containerized, and extensible framework for secure-by-design digital twin deployments in mission-critical infrastructures

Ruoxi Sun, Minhui Xue, Gareth Tyson et al.

Numerous open-source and commercial malware detectors are available. However, their efficacy is threatened by new adversarial attacks, whereby malware attempts to evade detection, e.g., by performing feature-space manipulation. In this work, we propose an explainability-guided and model-agnostic testing framework for robustness of malware detectors when confronted with adversarial attacks. The framework introduces the concept of Accrued Malicious Magnitude (AMM) to identify which malware features could be manipulated to maximize the likelihood of evading detection. We then use this framework to test several state-of-the-art malware detectors' abilities to detect manipulated malware. We find that (i) commercial antivirus engines are vulnerable to AMM-guided test cases; (ii) the ability of a manipulated malware generated using one detector to evade detection by another detector (i.e., transferability) depends on the overlap of features with large AMM values between the different detectors; and (iii) AMM values effectively measure the fragility of features (i.e., capability of feature-space manipulation to flip the prediction results) and explain the robustness of malware detectors facing evasion attacks. Our findings shed light on the limitations of current malware detectors, as well as how they can be improved.

Xing Su, Shan Xue, Fanzhen Liu et al.

A community reveals the features and connections of its members that are different from those in other communities in a network. Detecting communities is of great significance in network analysis. Despite the classical spectral clustering and statistical inference methods, we notice a significant development of deep learning techniques for community detection in recent years with their advantages in handling high dimensional network data. Hence, a comprehensive overview of community detection's latest progress through deep learning is timely to academics and practitioners. This survey devises and proposes a new taxonomy covering different state-of-the-art methods, including deep learning-based models upon deep neural networks, deep nonnegative matrix factorization and deep sparse filtering. The main category, i.e., deep neural networks, is further divided into convolutional networks, graph attention networks, generative adversarial networks and autoencoders. The survey also summarizes the popular benchmark data sets, evaluation metrics, and open-source implementations to address experimentation settings. We then discuss the practical applications of community detection in various domains and point to implementation scenarios. Finally, we outline future directions by suggesting challenging topics in this fast-growing deep learning field.

Nicholas D'Silva, Surya Nepal, Salil S. Kanhere

Graph data is increasingly prevalent across domains, offering analytical value but raising significant privacy concerns. Edges may encode sensitive relationships, while node attributes may contain sensitive entity or personal data. Differential Privacy (DP) has gained traction for its strong guarantees, yet applying DP to graphs is challenging because of their complex relational structure, leading to trade-offs between privacy and utility. Existing methods vary in privacy definitions, utility goals, and contextual settings, complicating comparison. For practitioners, this is compounded by DP's interpretability issues, contributing to misleading protection claims. To address this, we propose a novel systemisation of existing methods tailored to practical considerations and adaptable to varying practitioner objectives. Our contributions include: (i) a comprehensive survey of differentially private graph release methods; (ii) identification of key vulnerabilities; and (iii) a practitioner-oriented, objective-based framework to guide the selection, interpretation, and sound evaluation of existing methods. We demonstrate the use of our systemisation through two exemplary scenarios in which we assume the role of a social network analyst, apply it, and conduct evaluations in accordance with our framework. Together, these two illustrative instantiations ultimately provide a unified benchmark for state-of-the-art methods in the social networks domain.

Erik Buchholz, Alsharif Abuadbba, Shuo Wang et al.

While location trajectories represent a valuable data source for analyses and location-based services, they can reveal sensitive information, such as political and religious preferences. Differentially private publication mechanisms have been proposed to allow for analyses under rigorous privacy guarantees. However, the traditional protection schemes suffer from a limiting privacy-utility trade-off and are vulnerable to correlation and reconstruction attacks. Synthetic trajectory data generation and release represent a promising alternative to protection algorithms. While initial proposals achieve remarkable utility, they fail to provide rigorous privacy guarantees. This paper proposes a framework for designing a privacy-preserving trajectory publication approach by defining five design goals, particularly stressing the importance of choosing an appropriate Unit of Privacy. Based on this framework, we briefly discuss the existing trajectory protection approaches, emphasising their shortcomings. This work focuses on the systematisation of the state-of-the-art generative models for trajectories in the context of the proposed framework. We find that no existing solution satisfies all requirements. Thus, we perform an experimental study evaluating the applicability of six sequential generative models to the trajectory domain. Finally, we conclude that a generative trajectory model providing semantic guarantees remains an open research question and propose concrete next steps for future research.

David D. Nguyen, David Liebowitz, Surya Nepal et al.

Honeyfiles are security assets designed to attract and detect intruders on compromised systems. Honeyfiles are a type of honeypot that mimic real, sensitive documents, creating the illusion of the presence of valuable data. Interaction with a honeyfile reveals the presence of an intruder, and can provide insights into their goals and intentions. Their practical use, however, is limited by the time, cost and effort associated with manually creating realistic content. The introduction of large language models has made high-quality text generation accessible, but honeyfiles contain a variety of content including charts, tables and images. This content needs to be plausible and realistic, as well as semantically consistent both within honeyfiles and with the real documents they mimic, to successfully deceive an intruder. In this paper, we focus on an important component of the honeyfile content generation problem: document charts. Charts are ubiquitous in corporate documents and are commonly used to communicate quantitative and scientific data. Existing image generation models, such as DALL-E, are rather prone to generating charts with incomprehensible text and unconvincing data. We take a multi-modal approach to this problem by combining two purpose-built generative models: a multitask Transformer and a specialized multi-head autoencoder. The Transformer generates realistic captions and plot text, while the autoencoder generates the underlying tabular data for the plot. To advance the field of automated honeyplot generation, we also release a new document-chart dataset and propose a novel metric Keyword Semantic Matching (KSM). This metric measures the semantic consistency between keywords of a corpus and a smaller bag of words. Extensive experiments demonstrate excellent performance against multiple large language models, including ChatGPT and GPT4.

Hua Ma, Ruoxi Sun, Minhui Xue et al.

Accurate time-series forecasting is increasingly critical for planning and operations in low-carbon power systems. Emerging time-series large language models (TS-LLMs) now deliver this capability at scale, requiring no task-specific retraining, and are quickly becoming essential components within the Internet-of-Energy (IoE) ecosystem. However, their real-world deployment is complicated by a critical vulnerability: adversarial examples (AEs). Detecting these AEs is challenging because (i) adversarial perturbations are optimized across the entire input sequence and exploit global temporal dependencies, which renders local detection methods ineffective, and (ii) unlike traditional forecasting models with fixed input dimensions, TS-LLMs accept sequences of variable length, increasing variability that complicates detection. To address these challenges, we propose a plug-in detection framework that capitalizes on the TS-LLM's own variable-length input capability. Our method uses sampling-induced divergence as a detection signal. Given an input sequence, we generate multiple shortened variants and detect AEs by measuring the consistency of their forecasts: Benign sequences tend to produce stable predictions under sampling, whereas adversarial sequences show low forecast similarity, because perturbations optimized for a full-length sequence do not transfer reliably to shorter, differently-structured subsamples. We evaluate our approach on three representative TS-LLMs (TimeGPT, TimesFM, and TimeLLM) across three energy datasets: ETTh2 (Electricity Transformer Temperature), NI (Hourly Energy Consumption), and Consumption (Hourly Electricity Consumption and Production). Empirical results confirm strong and robust detection performance across both black-box and white-box attack scenarios, highlighting its practicality as a reliable safeguard for TS-LLM forecasting in real-world energy systems.

Van Nguyen, Surya Nepal, Xingliang Yuan et al.

Software vulnerabilities (SVs) pose a critical threat to safety-critical systems, driving the adoption of AI-based approaches such as machine learning and deep learning for software vulnerability detection. Despite promising results, most existing methods are limited to a single programming language. This is problematic given the multilingual nature of modern software, which is often complex and written in multiple languages. Current approaches often face challenges in capturing both shared and language-specific knowledge of source code, which can limit their performance on diverse programming languages and real-world codebases. To address this gap, we propose MULVULN, a novel multilingual vulnerability detection approach that learns from source code across multiple languages. MULVULN captures both the shared knowledge that generalizes across languages and the language-specific knowledge that reflects unique coding conventions. By integrating these aspects, it achieves more robust and effective detection of vulnerabilities in real-world multilingual software systems. The rigorous and extensive experiments on the real-world and diverse REEF dataset, consisting of 4,466 CVEs with 30,987 patches across seven programming languages, demonstrate the superiority of MULVULN over thirteen effective and state-of-the-art baselines. Notably, MULVULN achieves substantially higher F1-score, with improvements ranging from 1.45% to 23.59% compared to the baseline methods.

Fanzhen Liu, Alsharif Abuadbba, Kristen Moore et al.

In an era where misinformation spreads freely, fact-checking (FC) plays a crucial role in verifying claims and promoting reliable information. While automated fact-checking (AFC) has advanced significantly, existing systems remain vulnerable to adversarial attacks that manipulate or generate claims, evidence, or claim-evidence pairs. These attacks can distort the truth, mislead decision-makers, and ultimately undermine the reliability of FC models. Despite growing research interest in adversarial attacks against AFC systems, a comprehensive, holistic overview of key challenges remains lacking. These challenges include understanding attack strategies, assessing the resilience of current models, and identifying ways to enhance robustness. This survey provides the first in-depth review of adversarial attacks targeting FC, categorizing existing attack methodologies and evaluating their impact on AFC systems. Additionally, we examine recent advancements in adversary-aware defenses and highlight open research questions that require further exploration. Our findings underscore the urgent need for resilient FC frameworks capable of withstanding adversarial manipulations in pursuit of preserving high verification accuracy.

Fanzhen Liu, Xiaoxiao Ma, Jian Yang et al.

Enhancing the interpretability of graph neural networks (GNNs) is crucial to ensure their safe and fair deployment. Recent work has introduced self-explainable GNNs that generate explanations as part of training, improving both faithfulness and efficiency. Some of these models, such as ProtGNN and PGIB, learn class-specific prototypes, offering a potential pathway toward class-level explanations. However, their evaluations focus solely on instance-level explanations, leaving open the question of whether these prototypes meaningfully generalize across instances of the same class. In this paper, we introduce GraphOracle, a novel self-explainable GNN framework designed to generate and evaluate class-level explanations for GNNs. Our model jointly learns a GNN classifier and a set of structured, sparse subgraphs that are discriminative for each class. We propose a novel integrated training that captures graph$\unicode{x2013}$subgraph$\unicode{x2013}$prediction dependencies efficiently and faithfully, validated through a masking-based evaluation strategy. This strategy enables us to retroactively assess whether prior methods like ProtGNN and PGIB deliver effective class-level explanations. Our results show that they do not. In contrast, GraphOracle achieves superior fidelity, explainability, and scalability across a range of graph classification tasks. We further demonstrate that GraphOracle avoids the computational bottlenecks of previous methods$\unicode{x2014}$like Monte Carlo Tree Search$\unicode{x2014}$by using entropy-regularized subgraph selection and lightweight random walk extraction, enabling faster and more scalable training. These findings position GraphOracle as a practical and principled solution for faithful class-level self-explainability in GNNs.

Erik Buchholz, Natasha Fernandes, David D. Nguyen et al.

While location trajectories offer valuable insights, they also reveal sensitive personal information. Differential Privacy (DP) offers formal protection, but achieving a favourable utility-privacy trade-off remains challenging. Recent works explore deep learning-based generative models to produce synthetic trajectories. However, current models lack formal privacy guarantees and rely on conditional information derived from real data during generation. This work investigates the utility cost of enforcing DP in such models, addressing three research questions across two datasets and eleven utility metrics. (1) We evaluate how DP-SGD, the standard DP training method for deep learning, affects the utility of state-of-the-art generative models. (2) Since DP-SGD is limited to unconditional models, we propose a novel DP mechanism for conditional generation that provides formal guarantees and assess its impact on utility. (3) We analyse how model types - Diffusion, VAE, and GAN - affect the utility-privacy trade-off. Our results show that DP-SGD significantly impacts performance, although some utility remains if the datasets is sufficiently large. The proposed DP mechanism improves training stability, particularly when combined with DP-SGD, for unstable models such as GANs and on smaller datasets. Diffusion models yield the best utility without guarantees, but with DP-SGD, GANs perform best, indicating that the best non-private model is not necessarily optimal when targeting formal guarantees. In conclusion, DP trajectory generation remains a challenging task, and formal guarantees are currently only feasible with large datasets and in constrained use cases.

Roelien C. Timmer, David Liebowitz, Surya Nepal et al.

Honeyfiles are a particularly useful type of honeypot: fake files deployed to detect and infer information from malicious behaviour. This paper considers the challenge of naming honeyfiles so they are camouflaged when placed amongst real files in a file system. Based on cosine distances in semantic vector spaces, we develop two metrics for filename camouflage: one based on simple averaging and one on clustering with mixture fitting. We evaluate and compare the metrics, showing that both perform well on a publicly available GitHub software repository dataset.

Shahroz Tariq, Mohan Baruwal Chhetri, Surya Nepal et al.

This paper introduces A2C, a multi-stage collaborative decision framework designed to enable robust decision-making within human-AI teams. Drawing inspiration from concepts such as rejection learning and learning to defer, A2C incorporates AI systems trained to recognise uncertainty in their decisions and defer to human experts when needed. Moreover, A2C caters to scenarios where even human experts encounter limitations, such as in incident detection and response in cyber Security Operations Centres (SOC). In such scenarios, A2C facilitates collaborative explorations, enabling collective resolution of complex challenges. With support for three distinct decision-making modes in human-AI teams: Automated, Augmented, and Collaborative, A2C offers a flexible platform for developing effective strategies for human-AI collaboration. By harnessing the strengths of both humans and AI, it significantly improves the efficiency and effectiveness of complex decision-making in dynamic and evolving environments. To validate A2C's capabilities, we conducted extensive simulative experiments using benchmark datasets. The results clearly demonstrate that all three modes of decision-making can be effectively supported by A2C. Most notably, collaborative exploration by (simulated) human experts and AI achieves superior performance compared to AI in isolation, underscoring the framework's potential to enhance decision-making within human-AI teams.

David D. Nguyen, David Liebowitz, Surya Nepal et al.

In many real-world applications, from robotics to pedestrian trajectory prediction, there is a need to predict multiple real-valued outputs to represent several potential scenarios. Current deep learning techniques to address multiple-output problems are based on two main methodologies: (1) mixture density networks, which suffer from poor stability at high dimensions, or (2) multiple choice learning (MCL), an approach that uses $M$ single-output functions, each only producing a point estimate hypothesis. This paper presents a Mixture of Multiple-Output functions (MoM) approach using a novel variant of dropout, Multiple Hypothesis Dropout. Unlike traditional MCL-based approaches, each multiple-output function not only estimates the mean but also the variance for its hypothesis. This is achieved through a novel stochastic winner-take-all loss which allows each multiple-output function to estimate variance through the spread of its subnetwork predictions. Experiments on supervised learning problems illustrate that our approach outperforms existing solutions for reconstructing multimodal output distributions. Additional studies on unsupervised learning problems show that estimating the parameters of latent posterior distributions within a discrete autoencoder significantly improves codebook efficiency, sample quality, precision and recall.

M. A. P. Chamikara, Dongxi Liu, Seyit Camtepe et al.

Advanced adversarial attacks such as membership inference and model memorization can make federated learning (FL) vulnerable and potentially leak sensitive private data. Local differentially private (LDP) approaches are gaining more popularity due to stronger privacy notions and native support for data distribution compared to other differentially private (DP) solutions. However, DP approaches assume that the FL server (that aggregates the models) is honest (run the FL protocol honestly) or semi-honest (run the FL protocol honestly while also trying to learn as much information as possible). These assumptions make such approaches unrealistic and unreliable for real-world settings. Besides, in real-world industrial environments (e.g., healthcare), the distributed entities (e.g., hospitals) are already composed of locally running machine learning models (this setting is also referred to as the cross-silo setting). Existing approaches do not provide a scalable mechanism for privacy-preserving FL to be utilized under such settings, potentially with untrusted parties. This paper proposes a new local differentially private FL (named LDPFL) protocol for industrial settings. LDPFL can run in industrial settings with untrusted entities while enforcing stronger privacy guarantees than existing approaches. LDPFL shows high FL model performance (up to 98%) under small privacy budgets (e.g., epsilon = 0.5) in comparison to existing methods.

Zhi Zhang, Decheng Chen, Jiahao Qi et al.

Rowhammer has drawn much attention from both academia and industry in the past years as rowhammer exploitation poses severe consequences to system security. Since the first comprehensive study of rowhammer in 2014, a number of rowhammer attacks have been demonstrated against dynamic random access memory (DRAM)-based commodity systems to break software confidentiality, integrity and availability. Accordingly, numerous software defenses have been proposed to mitigate rowhammer attacks on commodity systems of either legacy (e.g., DDR3) or recent DRAM (e.g., DDR4). Besides, multiple hardware defenses (e.g., Target Row Refresh) from the industry have been deployed into recent DRAM to eliminate rowhammer, which we categorize as production defenses. In this paper, we systematize rowhammer attacks and defenses with a focus on DRAM-based commodity systems. Particularly, we have established a unified framework demonstrating how a rowhammer attack affects a commodity system. With the framework, we characterize existing attacks, shedding light on new attack vectors that have not yet been explored. We further leverage the framework to categorize software and production defenses, generalize their key defense strategies and summarize their key limitations, from which potential defense strategies are identified.

Kristen Moore, Cody J. Christopher, David Liebowitz et al.

Cyber deception is emerging as a promising approach to defending networks and systems against attackers and data thieves. However, despite being relatively cheap to deploy, the generation of realistic content at scale is very costly, due to the fact that rich, interactive deceptive technologies are largely hand-crafted. With recent improvements in Machine Learning, we now have the opportunity to bring scale and automation to the creation of realistic and enticing simulated content. In this work, we propose a framework to automate the generation of email and instant messaging-style group communications at scale. Such messaging platforms within organisations contain a lot of valuable information inside private communications and document attachments, making them an enticing target for an adversary. We address two key aspects of simulating this type of system: modelling when and with whom participants communicate, and generating topical, multi-party text to populate simulated conversation threads. We present the LogNormMix-Net Temporal Point Process as an approach to the first of these, building upon the intensity-free modeling approach of Shchur et al. to create a generative model for unicast and multi-cast communications. We demonstrate the use of fine-tuned, pre-trained language models to generate convincing multi-party conversation threads. A live email server is simulated by uniting our LogNormMix-Net TPP (to generate the communication timestamp, sender and recipients) with the language model, which generates the contents of the multi-party email threads. We evaluate the generated content with respect to a number of realism-based properties, that encourage a model to learn to generate content that will engage the attention of an adversary to achieve a deception outcome.

Yifeng Zheng, Cong Wang, Ruochen Wang et al.

Outsourcing decision tree inference services to the cloud is highly beneficial, yet raises critical privacy concerns on the proprietary decision tree of the model provider and the private input data of the client. In this paper, we design, implement, and evaluate a new system that allows highly efficient outsourcing of decision tree inference. Our system significantly improves upon the state-of-the-art in the overall online end-to-end secure inference service latency at the cloud as well as the local-side performance of the model provider. We first presents a new scheme which securely shifts most of the processing of the model provider to the cloud, resulting in a substantial reduction on the model provider's performance complexities. We further devise a scheme which substantially optimizes the performance for encrypted decision tree inference at the cloud, particularly the communication round complexities. The synergy of these techniques allows our new system to achieve up to $8 \times$ better overall online end-to-end secure inference latency at the cloud side over realistic WAN environment, as well as bring the model provider up to $19 \times$ savings in communication and $18 \times$ savings in computation.

Yansong Gao, Yang Su, Surya Nepal et al.

Building hardware security primitives with on-device memory fingerprints is a compelling proposition given the ubiquity of memory in electronic devices, especially for low-end Internet of Things devices for which cryptographic modules are often unavailable. However, the use of fingerprints in security functions is challenged by the small, but unpredictable variations in fingerprint reproductions from the same device due to measurement noise. Our study formulates a novel and pragmatic approach to achieve highly reliable fingerprints from device memories. We investigate the transformation of raw fingerprints into a noise-tolerant space where the generation of fingerprints is intrinsically highly reliable. We derive formal performance bounds to support practitioners to easily adopt our methods for applications. Subsequently, we demonstrate the expressive power of our formalization by using it to investigate the practicability of extracting noise-tolerant fingerprints from commodity devices. Together with extensive simulations, we have employed 119 chips from five different manufacturers for extensive experimental validations. Our results, including an end-to-end implementation demonstration with a low-cost wearable Bluetooth inertial sensor capable of on-demand and runtime key generation, show that key generators with failure rates less than $10^-6$ can be efficiently obtained with noise-tolerant fingerprints with a single fingerprint snapshot to support ease-of-enrollment.

Mahathir Almashor, Ejaz Ahmed, Benjamin Pick et al.

URLs are central to a myriad of cyber-security threats, from phishing to the distribution of malware. Their inherent ease of use and familiarity is continuously abused by attackers to evade defences and deceive end-users. Seemingly dissimilar URLs are being used in an organized way to perform phishing attacks and distribute malware. We refer to such behaviours as campaigns, with the hypothesis being that attacks are often coordinated to maximize success rates and develop evasion tactics. The aim is to gain better insights into campaigns, bolster our grasp of their characteristics, and thus aid the community devise more robust solutions. To this end, we performed extensive research and analysis into 311M records containing 77M unique real-world URLs that were submitted to VirusTotal from Dec 2019 to Jan 2020. From this dataset, 2.6M suspicious campaigns were identified based on their attached metadata, of which 77,810 were doubly verified as malicious. Using the 38.1M records and 9.9M URLs within these malicious campaigns, we provide varied insights such as their targeted victim brands as well as URL sizes and heterogeneity. Some surprising findings were observed, such as detection rates falling to just 13.27% for campaigns that employ more than 100 unique URLs. The paper concludes with several case-studies that illustrate the common malicious techniques employed by attackers to imperil users and circumvent defences.

Chandra Thapa, Kallol Krishna Karmakar, Alberto Huertas Celdran et al.

An integrated clinical environment (ICE) enables the connection and coordination of the internet of medical things around the care of patients in hospitals. However, ransomware attacks and their spread on hospital infrastructures, including ICE, are rising. Often the adversaries are targeting multiple hospitals with the same ransomware attacks. These attacks are detected by using machine learning algorithms. But the challenge is devising the anti-ransomware learning mechanisms and services under the following conditions: (1) provide immunity to other hospitals if one of them got the attack, (2) hospitals are usually distributed over geographical locations, and (3) direct data sharing is avoided due to privacy concerns. In this regard, this paper presents a federated distributed integrated clinical environment, aka. FedDICE. FedDICE integrates federated learning (FL), which is privacy-preserving learning, to SDN-oriented security architecture to enable collaborative learning, detection, and mitigation of ransomware attacks. We demonstrate the importance of FedDICE in a collaborative environment with up to four hospitals and four popular ransomware families, namely WannaCry, Petya, BadRabbit, and PowerGhost. Our results find that in both IID and non-IID data setups, FedDICE achieves the centralized baseline performance that needs direct data sharing for detection. However, as a trade-off to data privacy, FedDICE observes overhead in the anti-ransomware model training, e.g., 28x for the logistic regression model. Besides, FedDICE utilizes SDN's dynamic network programmability feature to remove the infected devices in ICE.

Keelan Evans, Alsharif Abuadbba, Tingmin Wu et al.

Spear Phishing is a harmful cyber-attack facing business and individuals worldwide. Considerable research has been conducted recently into the use of Machine Learning (ML) techniques to detect spear-phishing emails. ML-based solutions may suffer from zero-day attacks; unseen attacks unaccounted for in the training data. As new attacks emerge, classifiers trained on older data are unable to detect these new varieties of attacks resulting in increasingly inaccurate predictions. Spear Phishing detection also faces scalability challenges due to the growth of the required features which is proportional to the number of the senders within a receiver mailbox. This differs from traditional phishing attacks which typically perform only a binary classification between phishing and benign emails. Therefore, we devise a possible solution to these problems, named RAIDER: Reinforcement AIded Spear Phishing DEtectoR. A reinforcement-learning based feature evaluation system that can automatically find the optimum features for detecting different types of attacks. By leveraging a reward and penalty system, RAIDER allows for autonomous features selection. RAIDER also keeps the number of features to a minimum by selecting only the significant features to represent phishing emails and detect spear-phishing attacks. After extensive evaluation of RAIDER over 11,000 emails and across 3 attack scenarios, our results suggest that using reinforcement learning to automatically identify the significant features could reduce the dimensions of the required features by 55% in comparison to existing ML-based systems. It also improves the accuracy of detecting spoofing attacks by 4% from 90% to 94%. In addition, RAIDER demonstrates reasonable detection accuracy even against a sophisticated attack named Known Sender in which spear-phishing emails greatly resemble those of the impersonated sender.

Xiaotao Feng, Ruoxi Sun, Xiaogang Zhu et al.

The proliferation of Internet of Things (IoT) devices has made people's lives more convenient, but it has also raised many security concerns. Due to the difficulty of obtaining and emulating IoT firmware, the black-box fuzzing of IoT devices has become a viable option. However, existing black-box fuzzers cannot form effective mutation optimization mechanisms to guide their testing processes, mainly due to the lack of feedback. It is difficult or even impossible to apply existing grammar-based fuzzing strategies. Therefore, an efficient fuzzing approach with syntax inference is required in the IoT fuzzing domain. To address these critical problems, we propose a novel automatic black-box fuzzing for IoT firmware, termed Snipuzz. Snipuzz runs as a client communicating with the devices and infers message snippets for mutation based on the responses. Each snippet refers to a block of consecutive bytes that reflect the approximate code coverage in fuzzing. This mutation strategy based on message snippets considerably narrows down the search space to change the probing messages. We compared Snipuzz with four state-of-the-art IoT fuzzing approaches, i.e., IoTFuzzer, BooFuzz, Doona, and Nemesys. Snipuzz not only inherits the advantages of app-based fuzzing (e.g., IoTFuzzer, but also utilizes communication responses to perform efficient mutation. Furthermore, Snipuzz is lightweight as its execution does not rely on any prerequisite operations, such as reverse engineering of apps. We also evaluated Snipuzz on 20 popular real-world IoT devices. Our results show that Snipuzz could identify 5 zero-day vulnerabilities, and 3 of them could be exposed only by Snipuzz. All the newly discovered vulnerabilities have been confirmed by their vendors.

Shuo Wang, Lingjuan Lyu, Surya Nepal et al.

Previous robustness approaches for deep learning models such as data augmentation techniques via data transformation or adversarial training cannot capture real-world variations that preserve the semantics of the input, such as a change in lighting conditions. To bridge this gap, we present NaTra, an adversarial training scheme that is designed to improve the robustness of image classification algorithms. We target attributes of the input images that are independent of the class identification, and manipulate those attributes to mimic real-world natural transformations (NaTra) of the inputs, which are then used to augment the training dataset of the image classifier. Specifically, we apply \textit{Batch Inverse Encoding and Shifting} to map a batch of given images to corresponding disentangled latent codes of well-trained generative models. \textit{Latent Codes Expansion} is used to boost image reconstruction quality through the incorporation of extended feature maps. \textit{Unsupervised Attribute Directing and Manipulation} enables identification of the latent directions that correspond to specific attribute changes, and then produce interpretable manipulations of those attributes, thereby generating natural transformations to the input data. We demonstrate the efficacy of our scheme by utilizing the disentangled latent representations derived from well-trained GANs to mimic transformations of an image that are similar to real-world natural variations (such as lighting conditions or hairstyle), and train models to be invariant to these natural transformations. Extensive experiments show that our method improves generalization of classification models and increases its robustness to various real-world distortions

Shuo Wang, Surya Nepal, Kristen Moore et al.

The diversity and quantity of data warehouses, gathering data from distributed devices such as mobile devices, can enhance the success and robustness of machine learning algorithms. Federated learning enables distributed participants to collaboratively learn a commonly-shared model while holding data locally. However, it is also faced with expensive communication and limitations due to the heterogeneity of distributed data sources and lack of access to global data. In this paper, we investigate a practical distributed learning scenario where multiple downstream tasks (e.g., classifiers) could be efficiently learned from dynamically-updated and non-iid distributed data sources while providing local data privatization. We introduce a new distributed/collaborative learning scheme to address communication overhead via latent compression, leveraging global data while providing privatization of local data without additional cost due to encryption or perturbation. This scheme divides learning into (1) informative feature encoding, and transmitting the latent representation of local data to address communication overhead; (2) downstream tasks centralized at the server using the encoded codes gathered from each node to address computing overhead. Besides, a disentanglement strategy is applied to address the privatization of sensitive components of local data. Extensive experiments are conducted on image and speech datasets. The results demonstrate that downstream tasks on the compact latent representations with the privatization of local data can achieve comparable accuracy to centralized learning.

Yanjun Zhang, Guangdong Bai, Xue Li et al.

Federated learning enables multiple participants to collaboratively train a model without aggregating the training data. Although the training data are kept within each participant and the local gradients can be securely synthesized, recent studies have shown that such privacy protection is insufficient. The global model parameters that have to be shared for optimization are susceptible to leak information about training data. In this work, we propose Confined Gradient Descent (CGD) that enhances privacy of federated learning by eliminating the sharing of global model parameters. CGD exploits the fact that a gradient descent optimization can start with a set of discrete points and converges to another set at the neighborhood of the global minimum of the objective function. It lets the participants independently train on their local data, and securely share the sum of local gradients to benefit each other. We formally demonstrate CGD's privacy enhancement over traditional FL. We prove that less information is exposed in CGD compared to that of traditional FL. CGD also guarantees desired model accuracy. We theoretically establish a convergence rate for CGD. We prove that the loss of the proprietary models learned for each participant against a model learned by aggregated training data is bounded. Extensive experimental results on two real-world datasets demonstrate the performance of CGD is comparable with the centralized learning, with marginal differences on validation loss (mostly within 0.05) and accuracy (mostly within 1%).

Jihyeon Ryu, Yifeng Zheng, Yansong Gao et al.

Collaborative inference has recently emerged as an attractive framework for applying deep learning to Internet of Things (IoT) applications by splitting a DNN model into several subpart models among resource-constrained IoT devices and the cloud. However, the reconstruction attack was proposed recently to recover the original input image from intermediate outputs that can be collected from local models in collaborative inference. For addressing such privacy issues, a promising technique is to adopt differential privacy so that the intermediate outputs are protected with a small accuracy loss. In this paper, we provide the first systematic study to reveal insights regarding the effectiveness of differential privacy for collaborative inference against the reconstruction attack. We specifically explore the privacy-accuracy trade-offs for three collaborative inference models with four datasets (SVHN, GTSRB, STL-10, and CIFAR-10). Our experimental analysis demonstrates that differential privacy can practically be applied to collaborative inference when a dataset has small intra-class variations in appearance. With the (empirically) optimized privacy budget parameter in our study, the differential privacy technique incurs accuracy loss of 0.476%, 2.066%, 5.021%, and 12.454% on SVHN, GTSRB, STL-10, and CIFAR-10 datasets, respectively, while thwarting the reconstruction attack.

Siqi Ma, Juanru Li, Hyoungshick Kim et al.

A fundamental premise of SMS One-Time Password (OTP) is that the used pseudo-random numbers (PRNs) are uniquely unpredictable for each login session. Hence, the process of generating PRNs is the most critical step in the OTP authentication. An improper implementation of the pseudo-random number generator (PRNG) will result in predictable or even static OTP values, making them vulnerable to potential attacks. In this paper, we present a vulnerability study against PRNGs implemented for Android apps. A key challenge is that PRNGs are typically implemented on the server-side, and thus the source code is not accessible. To resolve this issue, we build an analysis tool, \sysname, to assess implementations of the PRNGs in an automated manner without the source code requirement. Through reverse engineering, \sysname identifies the apps using SMS OTP and triggers each app's login functionality to retrieve OTP values. It further assesses the randomness of the OTP values to identify vulnerable PRNGs. By analyzing 6,431 commercially used Android apps downloaded from \tool{Google Play} and \tool{Tencent Myapp}, \sysname identified 399 vulnerable apps that generate predictable OTP values. Even worse, 194 vulnerable apps use the OTP authentication alone without any additional security mechanisms, leading to insecure authentication against guessing attacks and replay attacks.

Yansong Gao, Minki Kim, Chandra Thapa et al.

Federated learning (FL) and split learning (SL) are state-of-the-art distributed machine learning techniques to enable machine learning training without accessing raw data on clients or end devices. However, their \emph{comparative training performance} under real-world resource-restricted Internet of Things (IoT) device settings, e.g., Raspberry Pi, remains barely studied, which, to our knowledge, have not yet been evaluated and compared, rendering inconvenient reference for practitioners. This work firstly provides empirical comparisons of FL and SL in real-world IoT settings regarding (i) learning performance with heterogeneous data distributions and (ii) on-device execution overhead. Our analyses in this work demonstrate that the learning performance of SL is better than FL under an imbalanced data distribution but worse than FL under an extreme non-IID data distribution. Recently, FL and SL are combined to form splitfed learning (SFL) to leverage each of their benefits (e.g., parallel training of FL and lightweight on-device computation requirement of SL). This work then considers FL, SL, and SFL, and mount them on Raspberry Pi devices to evaluate their performance, including training time, communication overhead, power consumption, and memory usage. Besides evaluations, we apply two optimizations. Firstly, we generalize SFL by carefully examining the possibility of a hybrid type of model training at the server-side. The generalized SFL merges sequential (dependent) and parallel (independent) processes of model training and is thus beneficial for a system with large-scaled IoT devices, specifically at the server-side operations. Secondly, we propose pragmatic techniques to substantially reduce the communication overhead by up to four times for the SL and (generalized) SFL.

Tom Roth, Yansong Gao, Alsharif Abuadbba et al.

Many adversarial attacks target natural language processing systems, most of which succeed through modifying the individual tokens of a document. Despite the apparent uniqueness of each of these attacks, fundamentally they are simply a distinct configuration of four components: a goal function, allowable transformations, a search method, and constraints. In this survey, we systematically present the different components used throughout the literature, using an attack-independent framework which allows for easy comparison and categorisation of components. Our work aims to serve as a comprehensive guide for newcomers to the field and to spark targeted research into refining the individual attack components.