Seyit Camtepe

Shuiqiao Yang, Bao Gia Doan, Paul Montague et al. · cambridge

Graph Neural Networks (GNNs) have achieved tremendous success in many graph mining tasks benefitting from the message passing strategy that fuses the local structure and node features for better graph representation learning. Despite the success of GNNs, and similar to other types of deep neural networks, GNNs are found to be vulnerable to unnoticeable perturbations on both graph structure and node features. Many adversarial attacks have been proposed to disclose the fragility of GNNs under different perturbation strategies to create adversarial examples. However, vulnerability of GNNs to successful backdoor attacks was only shown recently. In this paper, we disclose the TRAP attack, a Transferable GRAPh backdoor attack. The core attack principle is to poison the training dataset with perturbation-based triggers that can lead to an effective and transferable backdoor attack. The perturbation trigger for a graph is generated by performing the perturbation actions on the graph structure via a gradient based score matrix from a surrogate model. Compared with prior works, TRAP attack is different in several ways: i) it exploits a surrogate Graph Convolutional Network (GCN) model to generate perturbation triggers for a blackbox based backdoor attack; ii) it generates sample-specific perturbation triggers which do not have a fixed pattern; and iii) the attack transfers, for the first time in the context of GNNs, to different GNN models when trained with the forged poisoned training dataset. Through extensive evaluations on four real-world datasets, we demonstrate the effectiveness of the TRAP attack to build transferable backdoors in four different popular GNNs using four real-world datasets.

Van Nguyen, Trung Le, Chakkrit Tantithamthavorn et al.

Software vulnerabilities are a serious and crucial concern. Typically, in a program or function consisting of hundreds or thousands of source code statements, there are only a few statements causing the corresponding vulnerabilities. Most current approaches to vulnerability labelling are done on a function or program level by experts with the assistance of machine learning tools. Extending this approach to the code statement level is much more costly and time-consuming and remains an open problem. In this paper, we propose a novel end-to-end deep learning-based approach to identify the vulnerability-relevant code statements of a specific function. Inspired by the specific structures observed in real-world vulnerable code, we first leverage mutual information for learning a set of latent variables representing the relevance of the source code statements to the corresponding function's vulnerability. We then propose novel clustered spatial contrastive learning in order to further improve the representation learning and the robust selection process of vulnerability-relevant code statements. Experimental results on real-world datasets of 200k+ C/C++ functions show the superiority of our method over other state-of-the-art baselines. In general, our method obtains a higher performance in VCP, VCA, and Top-10 ACC measures of between 3% to 14% over the baselines when running on real-world datasets in an unsupervised setting. Our released source code samples are publicly available at \href{https://github.com/vannguyennd/livuitcl}{https://github.com/vannguyennd/livuitcl.}

Michael Robinson, Sajal Halder, Muhammad Ejaz Ahmed et al.

Understanding vulnerability propagation is essential for assessing how vulnerabilities spread across components of a software package. This supports more accurate impact analysis and enhances threat detection and mitigation. In this paper, we investigate how a small number of vulnerable JavaScript packages contribute to the creation of a disproportionately large number of vulnerable packages. This paper presents insights from 1,515 reported vulnerabilities gathered from a custom-built vulnerability database containing 1,077,946 JavaScript packages sourced from `npm-follower' and their associated dependency networks. Dependency networks were constructed using the deps.dev API, with vulnerabilities identified by parsing package names and version numbers through the Google Open Source Vulnerability API. Our findings reveal that 61.30% (660,748) of packages are reliant on one or more dependency packages, and 21.60% (232,836) of total packages have at least one known vulnerability throughout their dependency networks -- of which most (42%) are of High severity. We also found that it takes, on average, approximately 4 years and 11 months to fix a vulnerable package from when the first vulnerable version is published on npm -- although publication times of vulnerabilities occur approximately 19 days after a fix is available. Finally, we observe a high concentration of frequently present vulnerabilities throughout dependency networks, with the top-7 most frequent vulnerabilities accounting for 25% of vulnerability cases and the top-23 most frequent accounting for 50%. Based on these findings, we propose recommendations for developers and package managers to mitigate the threat and occurrence of vulnerabilities within the npm dependency network and the broader software repository community.

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.

Yuanyuan Wei, Julian Jang-Jaccard, Wen Xu et al.

Anomaly detection for indoor air quality (IAQ) data has become an important area of research as the quality of air is closely related to human health and well-being. However, traditional statistics and shallow machine learning-based approaches in anomaly detection in the IAQ area could not detect anomalies involving the observation of correlations across several data points (i.e., often referred to as long-term dependences). We propose a hybrid deep learning model that combines LSTM with Autoencoder for anomaly detection tasks in IAQ to address this issue. In our approach, the LSTM network is comprised of multiple LSTM cells that work with each other to learn the long-term dependences of the data in a time-series sequence. Autoencoder identifies the optimal threshold based on the reconstruction loss rates evaluated on every data across all time-series sequences. Our experimental results, based on the Dunedin CO2 time-series dataset obtained through a real-world deployment of the schools in New Zealand, demonstrate a very high and robust accuracy rate (99.50%) that outperforms other similar models.

Larry Huynh, Jin Hong, Ajmal Mian et al.

Quantum-inspired Machine Learning (QiML) is a burgeoning field, receiving global attention from researchers for its potential to leverage principles of quantum mechanics within classical computational frameworks. However, current review literature often presents a superficial exploration of QiML, focusing instead on the broader Quantum Machine Learning (QML) field. In response to this gap, this survey provides an integrated and comprehensive examination of QiML, exploring QiML's diverse research domains including tensor network simulations, dequantized algorithms, and others, showcasing recent advancements, practical applications, and illuminating potential future research avenues. Further, a concrete definition of QiML is established by analyzing various prior interpretations of the term and their inherent ambiguities. As QiML continues to evolve, we anticipate a wealth of future developments drawing from quantum mechanics, quantum computing, and classical machine learning, enriching the field further. This survey serves as a guide for researchers and practitioners alike, providing a holistic understanding of QiML's current landscape and future directions.

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.

Yuanyuan Wei, Julian Jang-Jaccard, Fariza Sabrina et al.

A Distributed Denial-of-service (DDoS) attack is a malicious attempt to disrupt the regular traffic of a targeted server, service, or network by sending a flood of traffic to overwhelm the target or its surrounding infrastructure. As technology improves, new attacks have been developed by hackers. Traditional statistical and shallow machine learning techniques can detect superficial anomalies based on shallow data and feature selection, however, these approaches cannot detect unseen DDoS attacks. In this context, we propose a reconstruction-based anomaly detection model named LSTM-Autoencoder (LSTM-AE) which combines two deep learning-based models for detecting DDoS attack anomalies. The proposed structure of long short-term memory (LSTM) networks provides units that work with each other to learn the long short-term correlation of data within a time series sequence. Autoencoders are used to identify the optimal threshold based on the reconstruction error rates evaluated on each sample across all time-series sequences. As such, a combination model LSTM-AE can not only learn delicate sub-pattern differences in attacks and benign traffic flows, but also minimize reconstructed benign traffic to obtain a lower range reconstruction error, with attacks presenting a larger reconstruction error. In this research, we trained and evaluated our proposed LSTM-AE model on reflection-based DDoS attacks (DNS, LDAP, and SNMP). The results of our experiments demonstrate that our method performs better than other state-of-the-art methods, especially for LDAP attacks, with an accuracy of over 99.

Shigang Liu, Di Cao, Junae Kim et al.

Recently, deep learning has demonstrated promising results in enhancing the accuracy of vulnerability detection and identifying vulnerabilities in software. However, these techniques are still vulnerable to attacks. Adversarial examples can exploit vulnerabilities within deep neural networks, posing a significant threat to system security. This study showcases the susceptibility of deep learning models to adversarial attacks, which can achieve 100% attack success rate (refer to Table 5). The proposed method, EaTVul, encompasses six stages: identification of important samples using support vector machines, identification of important features using the attention mechanism, generation of adversarial data based on these features using ChatGPT, preparation of an adversarial attack pool, selection of seed data using a fuzzy genetic algorithm, and the execution of an evasion attack. Extensive experiments demonstrate the effectiveness of EaTVul, achieving an attack success rate of more than 83% when the snippet size is greater than 2. Furthermore, in most cases with a snippet size of 4, EaTVul achieves a 100% attack success rate. The findings of this research emphasize the necessity of robust defenses against adversarial attacks in software vulnerability detection.

Hevish Cowlessur, Chandra Thapa, Tansu Alpcan et al.

Quantum Machine Learning (QML) is an emerging field of research with potential applications to distributed collaborative learning, such as Split Learning (SL). SL allows resource-constrained clients to collaboratively train ML models with a server, reduce their computational overhead, and enable data privacy by avoiding raw data sharing. Although QML with SL has been studied, the problem remains open in resource-constrained environments where clients lack quantum computing capabilities. Additionally, data privacy leakage between client and server in SL poses risks of reconstruction attacks on the server side. To address these issues, we propose Hybrid Quantum Split Learning (HQSL), an application of Hybrid QML in SL. HQSL enables classical clients to train models with a hybrid quantum server and curtails reconstruction attacks. Additionally, we introduce a novel qubit-efficient data-loading technique for designing a quantum layer in HQSL, minimizing both the number of qubits and circuit depth. Evaluations on real hardware demonstrate HQSL's practicality under realistic quantum noise. Experiments on five datasets demonstrate HQSL's feasibility and ability to enhance classification performance compared to its classical models. Notably, HQSL achieves mean improvements of over 3% in both accuracy and F1-score for the Fashion-MNIST dataset, and over 1.5% in both metrics for the Speech Commands dataset. We expand these studies to include up to 100 clients, confirming HQSL's scalability. Moreover, we introduce a noise-based defense mechanism to tackle reconstruction attacks on the server side. Overall, HQSL enables classical clients to train collaboratively with a hybrid quantum server, improving model performance and resistance against reconstruction attacks.

Yuanyuan Wei, Julian Jang-Jaccard, Amardeep Singh et al.

DDoS attacks involve overwhelming a target system with a large number of requests or traffic from multiple sources, disrupting the normal traffic of a targeted server, service, or network. Distinguishing between legitimate traffic and malicious traffic is a challenging task. It is possible to classify legitimate traffic and malicious traffic and analysis the network traffic by using machine learning and deep learning techniques. However, an inter-model explanation implemented to classify a traffic flow whether is benign or malicious is an important investigation of the inner working theory of the model to increase the trustworthiness of the model. Explainable Artificial Intelligence (XAI) can explain the decision-making of the machine learning models that can be classified and identify DDoS traffic. In this context, we proposed a framework that can not only classify legitimate traffic and malicious traffic of DDoS attacks but also use SHAP to explain the decision-making of the classifier model. To address this concern, we first adopt feature selection techniques to select the top 20 important features based on feature importance techniques (e.g., XGB-based SHAP feature importance). Following that, the Multi-layer Perceptron Network (MLP) part of our proposed model uses the optimized features of the DDoS attack dataset as inputs to classify legitimate and malicious traffic. We perform extensive experiments with all features and selected features. The evaluation results show that the model performance with selected features achieves above 99\% accuracy. Finally, to provide interpretability, XAI can be adopted to explain the model performance between the prediction results and features based on global and local explanations by SHAP, which can better explain the results achieved by our proposed framework.

Saud Khan, Salman Durrani, Muhammad Basit Shahab et al.

We consider the multi-user detection (MUD) problem in uplink grant-free non-orthogonal multiple access (NOMA), where the access point has to identify the total number and correct identity of the active Internet of Things (IoT) devices and decode their transmitted data. We assume that IoT devices use complex spreading sequences and transmit information in a random-access manner following the burst-sparsity model, where some IoT devices transmit their data in multiple adjacent time slots with a high probability, while others transmit only once during a frame. Exploiting the temporal correlation, we propose an attention-based bidirectional long short-term memory (BiLSTM) network to solve the MUD problem. The BiLSTM network creates a pattern of the device activation history using forward and reverse pass LSTMs, whereas the attention mechanism provides essential context to the device activation points. By doing so, a hierarchical pathway is followed for detecting active devices in a grant-free scenario. Then, by utilising the complex spreading sequences, blind data detection for the estimated active devices is performed. The proposed framework does not require prior knowledge of device sparsity levels and channels for performing MUD. The results show that the proposed network achieves better performance compared to existing benchmark schemes.

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.

Vy Vo, Van Nguyen, Trung Le et al.

Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. A large number of interpreting methods focus on identifying explanatory input features, which generally fall into two main categories: attribution and selection. A popular attribution-based approach is to exploit local neighborhoods for learning instance-specific explainers in an additive manner. The process is thus inefficient and susceptible to poorly-conditioned samples. Meanwhile, many selection-based methods directly optimize local feature distributions in an instance-wise training framework, thereby being capable of leveraging global information from other inputs. However, they can only interpret single-class predictions and many suffer from inconsistency across different settings, due to a strict reliance on a pre-defined number of features selected. This work exploits the strengths of both methods and proposes a framework for learning local explanations simultaneously for multiple target classes. Our model explainer significantly outperforms additive and instance-wise counterparts on faithfulness with more compact and comprehensible explanations. We also demonstrate the capacity to select stable and important features through extensive experiments on various data sets and black-box model architectures.

Hevish Cowlessur, Chandra Thapa, Tansu Alpcan et al.

Multi-task learning (MTL) improves generalization and data efficiency by jointly learning related tasks through shared representations. In the widely used hard-parameter-sharing setting, a shared backbone is combined with task-specific prediction heads. However, task-specific parameters can grow rapidly with the number of tasks. Therefore, designing multi-task heads that preserve task specialization while improving parameter efficiency remains a key challenge. In Quantum Machine Learning (QML), variational quantum circuits (VQCs) provide a compact mechanism for mapping classical data to quantum states residing in high-dimensional Hilbert spaces, enabling expressive representations within constrained parameter budgets. We propose a parameter-efficient quantum multi-task learning (QMTL) framework that replaces conventional task-specific linear heads with a fully quantum prediction head in a hybrid architecture. The model consists of a VQC with a shared, task-independent quantum encoding stage, followed by lightweight task-specific ansatz blocks enabling localized task adaptation while maintaining compact parameterization. Under a controlled and capacity-matched formulation where the shared representation dimension grows with the number of tasks, our parameter-scaling analysis demonstrates that a standard classical head exhibits quadratic growth, whereas the proposed quantum head parameter cost scales linearly. We evaluate QMTL on three multi-task benchmarks spanning natural language processing, medical imaging, and multimodal sarcasm detection, where we achieve performance comparable to, and in some cases exceeding, classical hard-parameter-sharing baselines while consistently outperforming existing hybrid quantum MTL models with substantially fewer head parameters. We further demonstrate QMTL's executability on noisy simulators and real quantum hardware, illustrating its feasibility.

Wei Shao, Chandra Thapa, Rayne Holland et al.

Network slicing in 5G and the future 6G networks will enable the creation of multiple virtualized networks on a shared physical infrastructure. This innovative approach enables the provision of tailored networks to accommodate specific business types or industry users, thus delivering more customized and efficient services. However, the shared memory and cache in network slicing introduce security vulnerabilities that have yet to be fully addressed. In this paper, we introduce a reinforcement learning-based side-channel cache attack framework specifically designed for network slicing environments. Unlike traditional cache attack methods, our framework leverages reinforcement learning to dynamically identify and exploit cache locations storing sensitive information, such as authentication keys and user registration data. We assume that one slice network is compromised and demonstrate how the attacker can induce another shared slice to send registration requests, thereby estimating the cache locations of critical data. By formulating the cache timing channel attack as a reinforcement learning-driven guessing game between the attack slice and the victim slice, our model efficiently explores possible actions to pinpoint memory blocks containing sensitive information. Experimental results showcase the superiority of our approach, achieving a success rate of approximately 95\% to 98\% in accurately identifying the storage locations of sensitive data. This high level of accuracy underscores the potential risks in shared network slicing environments and highlights the need for robust security measures to safeguard against such advanced side-channel attacks.

William Holland, Chandra Thapa, Sarah Ali Siddiqui et al.

Large machine-learning training datasets can be distilled into small collections of informative synthetic data samples. These synthetic sets support efficient model learning and reduce the communication cost of data sharing. Thus, high-fidelity distilled data can support the efficient deployment of machine learning applications in distributed network environments. A naive way to construct a synthetic set in a distributed environment is to allow each client to perform local data distillation and to merge local distillations at a central server. However, the quality of the resulting set is impaired by heterogeneity in the distributions of the local data held by clients. To overcome this challenge, we introduce the first collaborative data distillation technique, called CollabDM, which captures the global distribution of the data and requires only a single round of communication between client and server. Our method outperforms the state-of-the-art one-shot learning method on skewed data in distributed learning environments. We also show the promising practical benefits of our method when applied to attack detection in 5G networks.

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.

Kristen Moore, Diksha Goel, Cody James Christopher et al.

Realistic network traffic simulation is critical for evaluating intrusion detection systems, stress-testing network protocols, and constructing high-fidelity environments for cybersecurity training. While attack traffic can often be layered into training environments using red-teaming or replay methods, generating authentic benign background traffic remains a core challenge -- particularly in simulating the complex temporal and communication dynamics of real-world networks. This paper introduces TempoNet, a novel generative model that combines multi-task learning with multi-mark temporal point processes to jointly model inter-arrival times and all packet- and flow-header fields. TempoNet captures fine-grained timing patterns and higher-order correlations such as host-pair behavior and seasonal trends, addressing key limitations of GAN-, LLM-, and Bayesian-based methods that fail to reproduce structured temporal variation. TempoNet produces temporally consistent, high-fidelity traces, validated on real-world datasets. Furthermore, we show that intrusion detection models trained on TempoNet-generated background traffic perform comparably to those trained on real data, validating its utility for real-world security applications.

Derui Wang, Kristen Moore, Diksha Goel et al.

Deep reinforcement learning (DRL) has gained widespread adoption in control and decision-making tasks due to its strong performance in dynamic environments. However, DRL agents are vulnerable to noisy observations and adversarial attacks, and concerns about the adversarial robustness of DRL systems have emerged. Recent efforts have focused on addressing these robustness issues by establishing rigorous theoretical guarantees for the returns achieved by DRL agents in adversarial settings. Among these approaches, policy smoothing has proven to be an effective and scalable method for certifying the robustness of DRL agents. Nevertheless, existing certifiably robust DRL relies on policies trained with simple Gaussian augmentations, resulting in a suboptimal trade-off between certified robustness and certified return. To address this issue, we introduce a novel paradigm dubbed \texttt{C}ertified-r\texttt{A}dius-\texttt{M}aximizing \texttt{P}olicy (\texttt{CAMP}) training. \texttt{CAMP} is designed to enhance DRL policies, achieving better utility without compromising provable robustness. By leveraging the insight that the global certified radius can be derived from local certified radii based on training-time statistics, \texttt{CAMP} formulates a surrogate loss related to the local certified radius and optimizes the policy guided by this surrogate loss. We also introduce \textit{policy imitation} as a novel technique to stabilize \texttt{CAMP} training. Experimental results demonstrate that \texttt{CAMP} significantly improves the robustness-return trade-off across various tasks. Based on the results, \texttt{CAMP} can achieve up to twice the certified expected return compared to that of baselines. Our code is available at https://github.com/NeuralSec/camp-robust-rl.

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.

Ahmad Mohsin, Helge Janicke, Ahmed Ibrahim et al.

This article presents a structured framework for Human-AI collaboration in Security Operations Centers (SOCs), integrating AI autonomy, trust calibration, and Human-in-the-loop decision making. Existing frameworks in SOCs often focus narrowly on automation, lacking systematic structures to manage human oversight, trust calibration, and scalable autonomy with AI. Many assume static or binary autonomy settings, failing to account for the varied complexity, criticality, and risk across SOC tasks considering Humans and AI collaboration. To address these limitations, we propose a novel autonomy tiered framework grounded in five levels of AI autonomy from manual to fully autonomous, mapped to Human-in-the-Loop (HITL) roles and task-specific trust thresholds. This enables adaptive and explainable AI integration across core SOC functions, including monitoring, protection, threat detection, alert triage, and incident response. The proposed framework differentiates itself from previous research by creating formal connections between autonomy, trust, and HITL across various SOC levels, which allows for adaptive task distribution according to operational complexity and associated risks. The framework is exemplified through a simulated cyber range that features the cybersecurity AI-Avatar, a fine-tuned LLM-based SOC assistant. The AI-Avatar case study illustrates human-AI collaboration for SOC tasks, reducing alert fatigue, enhancing response coordination, and strategically calibrating trust. This research systematically presents both the theoretical and practical aspects and feasibility of designing next-generation cognitive SOCs that leverage AI not to replace but to enhance human decision-making.

Yanqiu Wu, Eromanga Adermann, Chandra Thapa et al.

Radio signal classification plays a pivotal role in identifying the modulation scheme used in received radio signals, which is essential for demodulation and proper interpretation of the transmitted information. Researchers have underscored the high susceptibility of ML algorithms for radio signal classification to adversarial attacks. Such vulnerability could result in severe consequences, including misinterpretation of critical messages, interception of classified information, or disruption of communication channels. Recent advancements in quantum computing have revolutionized theories and implementations of computation, bringing the unprecedented development of Quantum Machine Learning (QML). It is shown that quantum variational classifiers (QVCs) provide notably enhanced robustness against classical adversarial attacks in image classification. However, no research has yet explored whether QML can similarly mitigate adversarial threats in the context of radio signal classification. This work applies QVCs to radio signal classification and studies their robustness to various adversarial attacks. We also propose the novel application of the approximate amplitude encoding (AAE) technique to encode radio signal data efficiently. Our extensive simulation results present that attacks generated on QVCs transfer well to CNN models, indicating that these adversarial examples can fool neural networks that they are not explicitly designed to attack. However, the converse is not true. QVCs primarily resist the attacks generated on CNNs. Overall, with comprehensive simulations, our results shed new light on the growing field of QML by bridging knowledge gaps in QAML in radio signal classification and uncovering the advantages of applying QML methods in practical applications.

Nazatul Haque Sultan, Yan Bo, Yansong Gao et al.

Federated Learning (FL) enables multiple users to collaboratively train a machine learning model without sharing raw data, making it suitable for privacy-sensitive applications. However, local model or weight updates can still leak sensitive information. Secure aggregation protocols mitigate this risk by ensuring that only the aggregated updates are revealed. Among these, single-setup protocols, where key generation and exchange occur only once, are the most efficient due to reduced communication and computation overhead. However, existing single-setup protocols often lack support for dynamic user participation and do not provide strong privacy guarantees such as forward and backward secrecy. \par In this paper, we present a novel secure aggregation protocol that requires only a single setup for the entire FL training. Our protocol supports dynamic user participation, tolerates dropouts, and achieves both forward and backward secrecy. It leverages lightweight symmetric homomorphic encryption with a key negation technique to mask updates efficiently, eliminating the need for user-to-user communication. To defend against model inconsistency attacks, we introduce a low-overhead verification mechanism using message authentication codes (MACs). We provide formal security proofs under both semi-honest and malicious adversarial models and implement a full prototype. Experimental results show that our protocol reduces user-side computation by up to $99\%$ compared to state-of-the-art protocols like e-SeaFL (ACSAC'24), while maintaining competitive model accuracy. These features make our protocol highly practical for real-world FL deployments, especially on resource-constrained devices.

Wei Shao, Yuhao Wang, Rongguang He et al.

Existing defence mechanisms have demonstrated significant effectiveness in mitigating rule-based Denial-of-Service (DoS) attacks, leveraging predefined signatures and static heuristics to identify and block malicious traffic. However, the emergence of AI-driven techniques presents new challenges to SDN security, potentially compromising the efficacy of existing defence mechanisms. In this paper, we introduce~AdaDoS, an adaptive attack model that disrupt network operations while evading detection by existing DoS-based detectors through adversarial reinforcement learning (RL). Specifically, AdaDoS models the problem as a competitive game between an attacker, whose goal is to obstruct network traffic without being detected, and a detector, which aims to identify malicious traffic. AdaDoS can solve this game by dynamically adjusting its attack strategy based on feedback from the SDN and the detector. Additionally, recognising that attackers typically have less information than defenders, AdaDoS formulates the DoS-like attack as a partially observed Markov decision process (POMDP), with the attacker having access only to delay information between attacker and victim nodes. We address this challenge with a novel reciprocal learning module, where the student agent, with limited observations, enhances its performance by learning from the teacher agent, who has full observational capabilities in the SDN environment. AdaDoS represents the first application of RL to develop DoS-like attack sequences, capable of adaptively evading both machine learning-based and rule-based DoS-like attack detectors.

Hevish Cowlessur, Tansu Alpcan, Chandra Thapa et al.

Efficiently embedding high-dimensional datasets onto noisy and low-qubit quantum systems is a significant barrier to practical Quantum Machine Learning (QML). Approaches such as quantum autoencoders can be constrained by current hardware capabilities and may exhibit vulnerabilities to reconstruction attacks due to their invertibility. We propose Quantum Principal Geodesic Analysis (qPGA), a novel, non-invertible method for dimensionality reduction and qubit-efficient encoding. Executed classically, qPGA leverages Riemannian geometry to project data onto the unit Hilbert sphere, generating outputs inherently suitable for quantum amplitude encoding. This technique preserves the neighborhood structure of high-dimensional datasets within a compact latent space, significantly reducing qubit requirements for amplitude encoding. We derive theoretical bounds quantifying qubit requirements for effective encoding onto noisy systems. Empirical results on MNIST, Fashion-MNIST, and CIFAR-10 show that qPGA preserves local structure more effectively than both quantum and hybrid autoencoders. Additionally, we demonstrate that qPGA enhances resistance to reconstruction attacks due to its non-invertible nature. In downstream QML classification tasks, qPGA can achieve over 99% accuracy and F1-score on MNIST and Fashion-MNIST, outperforming quantum-dependent baselines. Initial tests on real hardware and noisy simulators confirm its potential for noise-resilient performance, offering a scalable solution for advancing QML applications.

Zhiyu Zhu, Zhibo Jin, Hongsheng Hu et al.

AI systems, in particular with deep learning techniques, have demonstrated superior performance for various real-world applications. Given the need for tailored optimization in specific scenarios, as well as the concerns related to the exploits of subsurface vulnerabilities, a more comprehensive and in-depth testing AI system becomes a pivotal topic. We have seen the emergence of testing tools in real-world applications that aim to expand testing capabilities. However, they often concentrate on ad-hoc tasks, rendering them unsuitable for simultaneously testing multiple aspects or components. Furthermore, trustworthiness issues arising from adversarial attacks and the challenge of interpreting deep learning models pose new challenges for developing more comprehensive and in-depth AI system testing tools. In this study, we design and implement a testing tool, \tool, to comprehensively and effectively evaluate AI systems. The tool extensively assesses multiple measurements towards adversarial robustness, model interpretability, and performs neuron analysis. The feasibility of the proposed testing tool is thoroughly validated across various modalities, including image classification, object detection, and text classification. Extensive experiments demonstrate that \tool is the state-of-the-art tool for a comprehensive assessment of the robustness and trustworthiness of AI systems. Our research sheds light on a general solution for AI systems testing landscape.

Diksha Goel, Kristen Moore, Mingyu Guo et al.

This paper addresses a significant gap in Autonomous Cyber Operations (ACO) literature: the absence of effective edge-blocking ACO strategies in dynamic, real-world networks. It specifically targets the cybersecurity vulnerabilities of organizational Active Directory (AD) systems. Unlike the existing literature on edge-blocking defenses which considers AD systems as static entities, our study counters this by recognizing their dynamic nature and developing advanced edge-blocking defenses through a Stackelberg game model between attacker and defender. We devise a Reinforcement Learning (RL)-based attack strategy and an RL-assisted Evolutionary Diversity Optimization-based defense strategy, where the attacker and defender improve each other strategy via parallel gameplay. To address the computational challenges of training attacker-defender strategies on numerous dynamic AD graphs, we propose an RL Training Facilitator that prunes environments and neural networks to eliminate irrelevant elements, enabling efficient and scalable training for large graphs. We extensively train the attacker strategy, as a sophisticated attacker model is essential for a robust defense. Our empirical results successfully demonstrate that our proposed approach enhances defender's proficiency in hardening dynamic AD graphs while ensuring scalability for large-scale AD.

Wei Shao, Rongyi Zhu, Cai Yang et al.

Spatiotemporal data is prevalent in a wide range of edge devices, such as those used in personal communication and financial transactions. Recent advancements have sparked a growing interest in integrating spatiotemporal analysis with large-scale language models. However, spatiotemporal data often contains sensitive information, making it unsuitable for open third-party access. To address this challenge, we propose a Graph-GAN-based model for generating privacy-protected spatiotemporal data. Our approach incorporates spatial and temporal attention blocks in the discriminator and a spatiotemporal deconvolution structure in the generator. These enhancements enable efficient training under Gaussian noise to achieve differential privacy. Extensive experiments conducted on three real-world spatiotemporal datasets validate the efficacy of our model. Our method provides a privacy guarantee while maintaining the data utility. The prediction model trained on our generated data maintains a competitive performance compared to the model trained on the original data.

Derui Wang, Minhui Xue, Bo Li et al.

The exploitation of publicly accessible data has led to escalating concerns regarding data privacy and intellectual property (IP) breaches in the age of artificial intelligence. To safeguard both data privacy and IP-related domain knowledge, efforts have been undertaken to render shared data unlearnable for unauthorized models in the wild. Existing methods apply empirically optimized perturbations to the data in the hope of disrupting the correlation between the inputs and the corresponding labels such that the data samples are converted into Unlearnable Examples (UEs). Nevertheless, the absence of mechanisms to verify the robustness of UEs against uncertainty in unauthorized models and their training procedures engenders several under-explored challenges. First, it is hard to quantify the unlearnability of UEs against unauthorized adversaries from different runs of training, leaving the soundness of the defense in obscurity. Particularly, as a prevailing evaluation metric, empirical test accuracy faces generalization errors and may not plausibly represent the quality of UEs. This also leaves room for attackers, as there is no rigid guarantee of the maximal test accuracy achievable by attackers. Furthermore, we find that a simple recovery attack can restore the clean-task performance of the classifiers trained on UEs by slightly perturbing the learned weights. To mitigate the aforementioned problems, in this paper, we propose a mechanism for certifying the so-called $(q, η)$-Learnability of an unlearnable dataset via parametric smoothing. A lower certified $(q, η)$-Learnability indicates a more robust and effective protection over the dataset. Concretely, we 1) improve the tightness of certified $(q, η)$-Learnability and 2) design Provably Unlearnable Examples (PUEs) which have reduced $(q, η)$-Learnability.

Reena Zelenkova, Jack Swallow, M. A. P. Chamikara et al.

Biometric data, such as face images, are often associated with sensitive information (e.g medical, financial, personal government records). Hence, a data breach in a system storing such information can have devastating consequences. Deep learning is widely utilized for face recognition (FR); however, such models are vulnerable to backdoor attacks executed by malicious parties. Backdoor attacks cause a model to misclassify a particular class as a target class during recognition. This vulnerability can allow adversaries to gain access to highly sensitive data protected by biometric authentication measures or allow the malicious party to masquerade as an individual with higher system permissions. Such breaches pose a serious privacy threat. Previous methods integrate noise addition mechanisms into face recognition models to mitigate this issue and improve the robustness of classification against backdoor attacks. However, this can drastically affect model accuracy. We propose a novel and generalizable approach (named BA-BAM: Biometric Authentication - Backdoor Attack Mitigation), that aims to prevent backdoor attacks on face authentication deep learning models through transfer learning and selective image perturbation. The empirical evidence shows that BA-BAM is highly robust and incurs a maximal accuracy drop of 2.4%, while reducing the attack success rate to a maximum of 20%. Comparisons with existing approaches show that BA-BAM provides a more practical backdoor mitigation approach for face recognition.

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.

Jinting Zhu, Julian Jang-Jaccard, Amardeep Singh et al.

Ransomware defense solutions that can quickly detect and classify different ransomware classes to formulate rapid response plans have been in high demand in recent years. Though the applicability of adopting deep learning techniques to provide automation and self-learning provision has been proven in many application domains, the lack of data available for ransomware (and other malware)samples has been raised as a barrier to developing effective deep learning-based solutions. To address this concern, we propose a few-shot meta-learning based Siamese Neural Network that not only detects ransomware attacks but is able to classify them into different classes. Our proposed model utilizes the entropy feature directly extracted from ransomware binary files to retain more fine-grained features associated with different ransomware signatures. These entropy features are used further to train and optimize our model using a pre-trained network (e.g. VGG-16) in a meta-learning fashion. This approach generates more accurate weight factors, compared to feature images are used, to avoid the bias typically associated with a model trained with a limited number of training samples. Our experimental results show that our proposed model is highly effective in providing a weighted F1-score exceeding the rate>86% compared

Chaoran Li, Xiao Chen, Ruoxi Sun et al.

The Android system manages access to sensitive APIs by permission enforcement. An application (app) must declare proper permissions before invoking specific Android APIs. However, there is no official documentation providing the complete list of permission-protected APIs and the corresponding permissions to date. Researchers have spent significant efforts extracting such API protection mapping from the Android API framework, which leverages static code analysis to determine if specific permissions are required before accessing an API. Nevertheless, none of them has attempted to analyze the protection mapping in the native library (i.e., code written in C and C++), an essential component of the Android framework that handles communication with the lower-level hardware, such as cameras and sensors. While the protection mapping can be utilized to detect various security vulnerabilities in Android apps, such as permission over-privilege and component hijacking, imprecise mapping will lead to false results in detecting such security vulnerabilities. To fill this gap, we develop a prototype system, named NatiDroid, to facilitate the cross-language static analysis to benchmark against two state-of-the-art tools, termed Axplorer and Arcade. We evaluate NatiDroid on more than 11,000 Android apps, including system apps from custom Android ROMs and third-party apps from the Google Play. Our NatiDroid can identify up to 464 new API-permission mappings, in contrast to the worst-case results derived from both Axplorer and Arcade, where approximately 71% apps have at least one false positive in permission over-privilege and up to 3.6% apps have at least one false negative in component hijacking. Additionally, we identify that 24 components with at least one Native-triggered component hijacking vulnerability are misidentified by two benchmarks.

Jinting Zhu, Julian Jang-Jaccard, Amardeep Singh et al.

Malware authors apply different techniques of control flow obfuscation, in order to create new malware variants to avoid detection. Existing Siamese neural network (SNN)-based malware detection methods fail to correctly classify different malware families when such obfuscated malware samples are present in the training dataset, resulting in high false-positive rates. To address this issue, we propose a novel task-aware few-shot-learning-based Siamese Neural Network that is resilient against the presence of malware variants affected by such control flow obfuscation techniques. Using the average entropy features of each malware family as inputs, in addition to the image features, our model generates the parameters for the feature layers, to more accurately adjust the feature embedding for different malware families, each of which has obfuscated malware variants. In addition, our proposed method can classify malware classes, even if there are only one or a few training samples available. Our model utilizes few-shot learning with the extracted features of a pre-trained network (e.g., VGG-16), to avoid the bias typically associated with a model trained with a limited number of training samples. Our proposed approach is highly effective in recognizing unique malware signatures, thus correctly classifying malware samples that belong to the same malware family, even in the presence of obfuscated malware variants. Our experimental results, validated by N-way on N-shot learning, show that our model is highly effective in classification accuracy, exceeding a rate \textgreater 91\%, compared to other similar methods.

Guoxin Sun, Tansu Alpcan, Benjamin I. P. Rubinstein et al.

Vehicle-to-vehicle communication enables autonomous platoons to boost traffic efficiency and safety, while ensuring string stability with a constant spacing policy. However, communication-based controllers are susceptible to a range of cyber-attacks. In this paper, we propose a distributed attack mitigation defense framework with a dual-mode control system reconfiguration scheme to prevent a compromised platoon member from causing collisions via message falsification attacks. In particular, we model it as a switched system consisting of a communication-based cooperative controller and a sensor-based local controller and derive conditions to achieve global uniform exponential stability (GUES) as well as string stability in the sense of platoon operation. The switching decision comes from game-theoretic analysis of the attacker and the defender's interactions. In this framework, the attacker acts as a leader that chooses whether to engage in malicious activities and the defender decides which control system to deploy with the help of an anomaly detector. Imperfect detection reports associate the game with imperfect information. A dedicated state constraint further enhances safety against bounded but aggressive message modifications in which a bounded solution may still violate practical constraint e.g. vehicles nearly crashing. Our formulation uniquely combines switched systems with security games to strategically improve the safety of such autonomous vehicle systems.

Praveen Joshi, Chandra Thapa, Seyit Camtepe et al.

Federated Learning (FL), Split Learning (SL), and SplitFed Learning (SFL) are three recent developments in distributed machine learning that are gaining attention due to their ability to preserve the privacy of raw data. Thus, they are widely applicable in various domains where data is sensitive, such as large-scale medical image classification, internet-of-medical-things, and cross-organization phishing email detection. SFL is developed on the confluence point of FL and SL. It brings the best of FL and SL by providing parallel client-side machine learning model updates from the FL paradigm and a higher level of model privacy (while training) by splitting the model between the clients and server coming from SL. However, SFL has communication and computation overhead at the client-side due to the requirement of client-side model synchronization. For the resource-constrained client-side, removal of such requirements is required to gain efficiency in the learning. In this regard, this paper studies SFL without client-side model synchronization. The resulting architecture is known as Multi-head Split Learning. Our empirical studies considering the ResNet18 model on MNIST data under IID data distribution among distributed clients find that Multi-head Split Learning is feasible. Its performance is comparable to the SFL. Moreover, SFL provides only 1%-2% better accuracy than Multi-head Split Learning on the MNIST test set. To further strengthen our results, we study the Multi-head Split Learning with various client-side model portions and its impact on the overall performance. To this end, our results find a minimal impact on the overall performance of the model.

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.

Muhammad Ejaz Ahmed, Hyoungshick Kim, Seyit Camtepe et al.

Ransomware is a growing threat that typically operates by either encrypting a victim's files or locking a victim's computer until the victim pays a ransom. However, it is still challenging to detect such malware timely with existing traditional malware detection techniques. In this paper, we present a novel ransomware detection system, called "Peeler" (Profiling kErnEl -Level Events to detect Ransomware). Peeler deviates from signatures for individual ransomware samples and relies on common and generic characteristics of ransomware depicted at the kernel-level. Analyzing diverse ransomware families, we observed ransomware's inherent behavioral characteristics such as stealth operations performed before the attack, file I/O request patterns, process spawning, and correlations among kernel-level events. Based on those characteristics, we develop Peeler that continuously monitors a target system's kernel events and detects ransomware attacks on the system. Our experimental results show that Peeler achieves more than 99\% detection rate with 0.58\% false-positive rate against 43 distinct ransomware families, containing samples from both crypto and screen-locker types of ransomware. For crypto ransomware, Peeler detects them promptly after only one file is lost (within 115 milliseconds on average). Peeler utilizes around 4.9\% of CPU time with only 9.8 MB memory under the normal workload condition. Our analysis demonstrates that Peeler can efficiently detect diverse malware families by monitoring their kernel-level events.

Anh Bui, Trung Le, He Zhao et al.

Contrastive learning (CL) has recently emerged as an effective approach to learning representation in a range of downstream tasks. Central to this approach is the selection of positive (similar) and negative (dissimilar) sets to provide the model the opportunity to `contrast' between data and class representation in the latent space. In this paper, we investigate CL for improving model robustness using adversarial samples. We first designed and performed a comprehensive study to understand how adversarial vulnerability behaves in the latent space. Based on this empirical evidence, we propose an effective and efficient supervised contrastive learning to achieve model robustness against adversarial attacks. Moreover, we propose a new sample selection strategy that optimizes the positive/negative sets by removing redundancy and improving correlation with the anchor. Extensive experiments show that our Adversarial Supervised Contrastive Learning (ASCL) approach achieves comparable performance with the state-of-the-art defenses while significantly outperforms other CL-based defense methods by using only $42.8\%$ positives and $6.3\%$ negatives.

Chandra Thapa, Seyit Camtepe

Precision health leverages information from various sources, including omics, lifestyle, environment, social media, medical records, and medical insurance claims to enable personalized care, prevent and predict illness, and precise treatments. It extensively uses sensing technologies (e.g., electronic health monitoring devices), computations (e.g., machine learning), and communication (e.g., interaction between the health data centers). As health data contain sensitive private information, including the identity of patient and carer and medical conditions of the patient, proper care is required at all times. Leakage of these private information affects the personal life, including bullying, high insurance premium, and loss of job due to the medical history. Thus, the security, privacy of and trust on the information are of utmost importance. Moreover, government legislation and ethics committees demand the security and privacy of healthcare data. Herein, in the light of precision health data security, privacy, ethical and regulatory requirements, finding the best methods and techniques for the utilization of the health data, and thus precision health is essential. In this regard, firstly, this paper explores the regulations, ethical guidelines around the world, and domain-specific needs. Then it presents the requirements and investigates the associated challenges. Secondly, this paper investigates secure and privacy-preserving machine learning methods suitable for the computation of precision health data along with their usage in relevant health projects. Finally, it illustrates the best available techniques for precision health data security and privacy with a conceptual system model that enables compliance, ethics clearance, consent management, medical innovations, and developments in the health domain.

Chandra Thapa, Jun Wen Tang, Alsharif Abuadbba et al.

The use of Artificial Intelligence (AI) to detect phishing emails is primarily dependent on large-scale centralized datasets, which opens it up to a myriad of privacy, trust, and legal issues. Moreover, organizations are loathed to share emails, given the risk of leakage of commercially sensitive information. So, it is uncommon to obtain sufficient emails to train a global AI model efficiently. Accordingly, privacy-preserving distributed and collaborative machine learning, particularly Federated Learning (FL), is a desideratum. Already prevalent in the healthcare sector, questions remain regarding the effectiveness and efficacy of FL-based phishing detection within the context of multi-organization collaborations. To the best of our knowledge, the work herein is the first to investigate the use of FL in email anti-phishing. This paper builds upon a deep neural network model, particularly RNN and BERT for phishing email detection. It analyzes the FL-entangled learning performance under various settings, including balanced and asymmetrical data distribution. Our results corroborate comparable performance statistics of FL in phishing email detection to centralized learning for balanced datasets, and low organization counts. Moreover, we observe a variation in performance when increasing organizational counts. For a fixed total email dataset, the global RNN based model suffers by a 1.8% accuracy drop when increasing organizational counts from 2 to 10. In contrast, BERT accuracy rises by 0.6% when going from 2 to 5 organizations. However, if we allow increasing the overall email dataset with the introduction of new organizations in the FL framework, the organizational level performance is improved by achieving a faster convergence speed. Besides, FL suffers in its overall global model performance due to highly unstable outputs if the email dataset distribution is highly asymmetric.

Pathum Chamikara Mahawaga Arachchige, Peter Bertok, Ibrahim Khalil et al.

Personally identifiable information (PII) can find its way into cyberspace through various channels, and many potential sources can leak such information. Data sharing (e.g. cross-agency data sharing) for machine learning and analytics is one of the important components in data science. However, due to privacy concerns, data should be enforced with strong privacy guarantees before sharing. Different privacy-preserving approaches were developed for privacy preserving data sharing; however, identifying the best privacy-preservation approach for the privacy-preservation of a certain dataset is still a challenge. Different parameters can influence the efficacy of the process, such as the characteristics of the input dataset, the strength of the privacy-preservation approach, and the expected level of utility of the resulting dataset (on the corresponding data mining application such as classification). This paper presents a framework named \underline{P}rivacy \underline{P}reservation \underline{a}s \underline{a} \underline{S}ervice (PPaaS) to reduce this complexity. The proposed method employs selective privacy preservation via data perturbation and looks at different dynamics that can influence the quality of the privacy preservation of a dataset. PPaaS includes pools of data perturbation methods, and for each application and the input dataset, PPaaS selects the most suitable data perturbation approach after rigorous evaluation. It enhances the usability of privacy-preserving methods within its pool; it is a generic platform that can be used to sanitize big data in a granular, application-specific manner by employing a suitable combination of diverse privacy-preserving algorithms to provide a proper balance between privacy and utility.

Ruoxi Sun, Wei Wang, Minhui Xue et al.

The rapid spread of COVID-19 has made manual contact tracing difficult. Thus, various public health authorities have experimented with automatic contact tracing using mobile applications (or "apps"). These apps, however, have raised security and privacy concerns. In this paper, we propose an automated security and privacy assessment tool, COVIDGUARDIAN, which combines identification and analysis of Personal Identification Information (PII), static program analysis and data flow analysis, to determine security and privacy weaknesses. Furthermore, in light of our findings, we undertake a user study to investigate concerns regarding contact tracing apps. We hope that COVIDGUARDIAN, and the issues raised through responsible disclosure to vendors, can contribute to the safe deployment of mobile contact tracing. As part of this, we offer concrete guidelines, and highlight gaps between user requirements and app performance.

Chandra Thapa, M. A. P. Chamikara, Seyit Camtepe et al.

Federated learning (FL) and split learning (SL) are two popular distributed machine learning approaches. Both follow a model-to-data scenario; clients train and test machine learning models without sharing raw data. SL provides better model privacy than FL due to the machine learning model architecture split between clients and the server. Moreover, the split model makes SL a better option for resource-constrained environments. However, SL performs slower than FL due to the relay-based training across multiple clients. In this regard, this paper presents a novel approach, named splitfed learning (SFL), that amalgamates the two approaches eliminating their inherent drawbacks, along with a refined architectural configuration incorporating differential privacy and PixelDP to enhance data privacy and model robustness. Our analysis and empirical results demonstrate that (pure) SFL provides similar test accuracy and communication efficiency as SL while significantly decreasing its computation time per global epoch than in SL for multiple clients. Furthermore, as in SL, its communication efficiency over FL improves with the number of clients. Besides, the performance of SFL with privacy and robustness measures is further evaluated under extended experimental settings.

Xiaogang Zhu, Xiaotao Feng, Tengyun Jiao et al.

Fuzzing is a promising technique for detecting security vulnerabilities. Newly developed fuzzers are typically evaluated in terms of the number of bugs found on vulnerable programs/binaries. However,existing corpora usually do not capture the features that prevent fuzzers from finding bugs, leading to ambiguous conclusions on the pros and cons of the fuzzers evaluated. A typical example is that Driller detects more bugs than AFL, but its evaluation cannot establish if the advancement of Driller stems from the concolic execution or not, since, for example, its ability in resolving a dataset`s magic values is unclear. In this paper, we propose to address the above problem by generating corpora based on search-hampering features. As a proof-of-concept, we have designed FEData, a prototype corpus that currently focuses on four search-hampering features to generate vulnerable programs for fuzz testing. Unlike existing corpora that can only answer "how", FEData can also further answer "why" by exposing (or understanding) the reasons for the identified weaknesses in a fuzzer. The "why" information serves as the key to the improvement of fuzzers.