Mustafa A. Mustafa

Xidan Song, Youcheng Sun, Mustafa A. Mustafa et al.

We present AIREPAIR, a platform for repairing neural networks. It features the integration of existing network repair tools. Based on AIREPAIR, one can run different repair methods on the same model, thus enabling the fair comparison of different repair techniques. We evaluate AIREPAIR with three state-of-the-art repair tools on popular deep-learning datasets and models. Our evaluation confirms the utility of AIREPAIR, by comparing and analyzing the results from different repair techniques. A demonstration is available at https://youtu.be/UkKw5neeWhw.

Xidan Song, Youcheng Sun, Mustafa A. Mustafa et al.

We present QNNRepair, the first method in the literature for repairing quantized neural networks (QNNs). QNNRepair aims to improve the accuracy of a neural network model after quantization. It accepts the full-precision and weight-quantized neural networks and a repair dataset of passing and failing tests. At first, QNNRepair applies a software fault localization method to identify the neurons that cause performance degradation during neural network quantization. Then, it formulates the repair problem into a linear programming problem of solving neuron weights parameters, which corrects the QNN's performance on failing tests while not compromising its performance on passing tests. We evaluate QNNRepair with widely used neural network architectures such as MobileNetV2, ResNet, and VGGNet on popular datasets, including high-resolution images. We also compare QNNRepair with the state-of-the-art data-free quantization method SQuant. According to the experiment results, we conclude that QNNRepair is effective in improving the quantized model's performance in most cases. Its repaired models have 24% higher accuracy than SQuant's in the independent validation set, especially for the ImageNet dataset.

Fatima Z. Abacha, Sin G. Teo, Yuanxiang Wu et al.

Federated Learning remains highly susceptible to backdoor attacks--malicious clients inject targeted behaviours into the global model. Existing defenses suffer from substantial false-positive rates under realistic non-independent and identically distributed (non-IID) data, incorrectly flagging benign clients and degrading model accuracy even when adversaries are correctly identified. We present FedSurrogate, a novel backdoor defense that addresses this limitation by combining bidirectional gradient alignment filtering with layer-adaptive anomaly detection. FedSurrogate performs selective clustering on security-critical layers identified via directional divergence analysis, concentrating the detection signal on a low-dimensional subspace. A bidirectional soft-filtering stage screens trusted clients for residual contamination while rescuing false positives from suspects, substantially reducing misclassifications under heterogeneous conditions. Rather than removing confirmed malicious updates, FedSurrogate replaces them with downscaled surrogate updates from structurally similar benign clients, preserving gradient diversity while neutralising adversarial influence. Extensive evaluations demonstrate that FedSurrogate maintains false-positive rates below 10% across all datasets and attack types, compared to 31-32% for the nearest comparably effective baseline, while achieving superior main-task accuracy and maintaining attack success rates below 2.1% across all tested datasets and attack types under challenging non-IID settings.

Fatima Abacha, Sin G. Teo, Lucas C. Cordeiro et al.

In heterogeneous scenarios where the data distribution amongst the Federated Learning (FL) participants is Non-Independent and Identically distributed (Non-IID), FL suffers from the well known problem of data heterogeneity. This leads the performance of FL to be significantly degraded, as the global model tends to struggle to converge. To solve this problem, we propose Differentially Private Synthetic Data Aided Federated Learning Using Foundation Models (DPSDA-FL), a novel data augmentation strategy that aids in homogenizing the local data present on the clients' side. DPSDA-FL improves the training of the local models by leveraging differentially private synthetic data generated from foundation models. We demonstrate the effectiveness of our approach by evaluating it on the benchmark image dataset: CIFAR-10. Our experimental results have shown that DPSDA-FL can improve class recall and classification accuracy of the global model by up to 26% and 9%, respectively, in FL with Non-IID issues.

Fatimah Aljaafari, Rafael Menezes, Mustafa A. Mustafa et al.

Internet of Things (IoT) consists of a large number of devices connected through a network, which exchange a high volume of data, thereby posing new security, privacy, and trust issues. One way to address these issues is ensuring data confidentiality using lightweight encryption algorithms for IoT protocols. However, the design and implementation of such protocols is an error-prone task; flaws in the implementation can lead to devastating security vulnerabilities. Here we propose a new verification approach named Encryption-BMC and Fuzzing (EBF), which combines Bounded Model Checking (BMC) and Fuzzing techniques to check for security vulnerabilities that arise from concurrent implementations of cyrptographic protocols, which include data race, thread leak, arithmetic overflow, and memory safety. EBF models IoT protocols as a client and server using POSIX threads, thereby simulating both entities' communication. It also employs static and dynamic verification to cover the system's state-space exhaustively. We evaluate EBF against three benchmarks. First, we use the concurrency benchmark from SV-COMP and show that it outperforms other state-of-the-art tools such as ESBMC, AFL, Lazy-CSeq, and TSAN with respect to bug finding. Second, we evaluate an open-source implementation called WolfMQTT. It is an MQTT client implementation that uses the WolfSSL library. We show that \tool detects a data race bug, which other approaches are unable to find. Third, to show the effectiveness of EBF, we replicate some known vulnerabilities in OpenSSL and CyaSSL (lately WolfSSL) libraries. EBF can detect the bugs in minimum time.

Yi Dong, Yingjie Wang, Mariana Gama et al.

In the realm of power systems, the increasing involvement of residential users in load forecasting applications has heightened concerns about data privacy. Specifically, the load data can inadvertently reveal the daily routines of residential users, thereby posing a risk to their property security. While federated learning (FL) has been employed to safeguard user privacy by enabling model training without the exchange of raw data, these FL models have shown vulnerabilities to emerging attack techniques, such as Deep Leakage from Gradients and poisoning attacks. To counteract these, we initially employ a Secure-Aggregation (SecAgg) algorithm that leverages multiparty computation cryptographic techniques to mitigate the risk of gradient leakage. However, the introduction of SecAgg necessitates the deployment of additional sub-center servers for executing the multiparty computation protocol, thereby escalating computational complexity and reducing system robustness, especially in scenarios where one or more sub-centers are unavailable. To address these challenges, we introduce a Markovian Switching-based distributed training framework, the convergence of which is substantiated through rigorous theoretical analysis. The Distributed Markovian Switching (DMS) topology shows strong robustness towards the poisoning attacks as well. Case studies employing real-world power system load data validate the efficacy of our proposed algorithm. It not only significantly minimizes communication complexity but also maintains accuracy levels comparable to traditional FL methods, thereby enhancing the scalability of our load forecasting algorithm.

Chibueze Peace Obioma, Youcheng Sun, Mustafa A. Mustafa

Federated learning (FL) enhances privacy and reduces communication cost for resource-constrained edge clients by supporting distributed model training at the edge. However, the heterogeneous nature of such devices produces diverse, non-independent, and identically distributed (non-IID) data, making the detection of backdoor attacks more challenging. In this paper, we propose a novel federated representative-attention-based defense mechanism, named FeRA, that leverages cross-client attention over internal feature representations to distinguish benign from malicious clients. FeRA computes an anomaly score based on representation reconstruction errors, effectively identifying clients whose internal activations significantly deviate from the group consensus. Our evaluation demonstrates FeRA's robustness across various FL scenarios, including challenging non-IID data distributions typical of edge devices. Experimental results show that it effectively reduces backdoor attack success rates while maintaining high accuracy on the main task. The method is model-agnostic, attack-agnostic, and does not require labeled reference data, making it well suited to heterogeneous and resource-limited edge deployments.

Xiaowei Huang, Wenjie Ruan, Wei Huang et al.

Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains. In response to their fast adoption in many industrial applications, this survey concerns their safety and trustworthiness. First, we review known vulnerabilities and limitations of the LLMs, categorising them into inherent issues, attacks, and unintended bugs. Then, we consider if and how the Verification and Validation (V&V) techniques, which have been widely developed for traditional software and deep learning models such as convolutional neural networks as independent processes to check the alignment of their implementations against the specifications, can be integrated and further extended throughout the lifecycle of the LLMs to provide rigorous analysis to the safety and trustworthiness of LLMs and their applications. Specifically, we consider four complementary techniques: falsification and evaluation, verification, runtime monitoring, and regulations and ethical use. In total, 370+ references are considered to support the quick understanding of the safety and trustworthiness issues from the perspective of V&V. While intensive research has been conducted to identify the safety and trustworthiness issues, rigorous yet practical methods are called for to ensure the alignment of LLMs with safety and trustworthiness requirements.

Kamil Erdayandi, Amrit Paudel, Lucas Cordeiro et al.

In this paper, we propose a decentralized, privacy-friendly energy trading platform (PFET) based on game theoretical approach - specifically Stackelberg competition. Unlike existing trading schemes, PFET provides a competitive market in which prices and demands are determined based on competition, and computations are performed in a decentralized manner which does not rely on trusted third parties. It uses homomorphic encryption cryptosystem to encrypt sensitive information of buyers and sellers such as sellers$'$ prices and buyers$'$ demands. Buyers calculate total demand on particular seller using an encrypted data and sensitive buyer profile data is hidden from sellers. Hence, privacy of both sellers and buyers is preserved. Through privacy analysis and performance evaluation, we show that PFET preserves users$'$ privacy in an efficient manner.

Iraklis Symeonidis, Dragos Rotaru, Mustafa A. Mustafa et al.

We propose HERMES, a scalable, secure, and privacy-enhancing system for users to share and access vehicles. HERMES securely outsources operations of vehicle access token generation to a set of untrusted servers. It builds on an earlier proposal, namely SePCAR [1], and extends the system design for improved efficiency and scalability. To cater to system and user needs for secure and private computations, HERMES utilizes and combines several cryptographic primitives with secure multiparty computation efficiently. It conceals secret keys of vehicles and transaction details from the servers, including vehicle booking details, access token information, and user and vehicle identities. It also provides user accountability in case of disputes. Besides, we provide semantic security analysis and prove that HERMES meets its security and privacy requirements. Last but not least, we demonstrate that HERMES is efficient and, in contrast to SePCAR, scales to a large number of users and vehicles, making it practical for real-world deployments. We build our evaluations with two different multiparty computation protocols: HtMAC-MiMC and CBC-MAC-AES. Our results demonstrate that HERMES with HtMAC-MiMC requires only approx 1,83 ms for generating an access token for a single-vehicle owner and approx 11,9 ms for a large branch of rental companies with over a thousand vehicles. It handles 546 and 84 access token generations per second, respectively. This results in HERMES being 696 (with HtMAC-MiMC) and 42 (with CBC-MAC-AES) times faster compared to in SePCAR for a single-vehicle owner access token generation. Furthermore, we show that HERMES is practical on the vehicle side, too, as access token operations performed on a prototype vehicle on-board unit take only approx 62,087 ms.

Fatimah Aljaafari, Lucas C. Cordeiro, Mustafa A. Mustafa

Internet of Things (IoT) is a system that consists of a large number of smart devices connected through a network. The number of these devices is increasing rapidly, which creates a massive and complex network with a vast amount of data communicated over that network. One way to protect this data in transit, i.e., to achieve data confidentiality, is to use lightweight encryption algorithms for IoT protocols. However, the design and implementation of such protocols is an error-prone task; flaws in the implementation can lead to devastating security vulnerabilities. These vulnerabilities can be exploited by an attacker and affect users' privacy. There exist various techniques to verify software and detect vulnerabilities. Bounded Model Checking (BMC) and Fuzzing are useful techniques to check the correctness of a software system concerning its specifications. Here we describe a framework called Encryption-BMC and Fuzzing (EBF) using combined BMC and fuzzing techniques. We evaluate the application of EBF verification framework on a case study, i.e., the S-MQTT protocol, to check security vulnerabilities in cryptographic protocols for IoT.

Omar M. Alhawi, Mustafa A. Mustafa, Lucas C. Cordeiro

The proliferation of Unmanned Aerial Vehicles (UAVs) embedded with vulnerable monolithic software has recently raised serious concerns about their security due to concurrency aspects and fragile communication links. However, verifying security in UAV software based on traditional testing remains an open challenge mainly due to scalability and deployment issues. Here we investigate software verification techniques to detect security vulnerabilities in typical UAVs. In particular, we investigate existing software analyzers and verifiers, which implement fuzzing and bounded model checking (BMC) techniques, to detect memory safety and concurrency errors. We also investigate fragility aspects related to the UAV communication link. All UAV components (e.g., position, velocity, and attitude control) heavily depend on the communication link. Our preliminary results show that fuzzing and BMC techniques can detect various software vulnerabilities, which are of particular interest to ensure security in UAVs. We were able to perform successful cyber-attacks via penetration testing against the UAV both connection and software system. As a result, we demonstrate real cyber-threats with the possibility of exploiting further security vulnerabilities in real-world UAV software in the foreseeable future.

Tim Van hamme, Vera Rimmer, Davy Preuveneers et al.

Authentication and authorization are critical security layers to protect a wide range of online systems, services and content. However, the increased prevalence of wearable and mobile devices, the expectations of a frictionless experience and the diverse user environments will challenge the way users are authenticated. Consumers demand secure and privacy-aware access from any device, whenever and wherever they are, without any obstacles. This paper reviews emerging trends and challenges with frictionless authentication systems and identifies opportunities for further research related to the enrollment of users, the usability of authentication schemes, as well as security and privacy trade-offs of mobile and wearable continuous authentication systems.

Mustafa A. Mustafa, Aysajan Abidin, Enrique Argones Rúa

This paper proposes a frictionless authentication system, provides a comprehensive security analysis of and proposes potential solutions for this system. It first presents a system that allows users to authenticate to services in a frictionless manner, i.e., without the need to perform any particular authentication-related actions. Based on this system model, the paper analyses security problems and potential privacy threats imposed on users, leading to the specification of a set of security and privacy requirements. These requirements can be used as a guidance on designing secure and privacy-friendly frictionless authentication systems. The paper also sketches three potential solutions for such systems and highlights their advantages and disadvantages.

Aysajan Abidin, Abdelrahaman Aly, Sara Cleemput et al.

This paper proposes two decentralised, secure and privacy-friendly protocols for local electricity trading and billing, respectively. The trading protocol employs a bidding algorithm based upon secure multiparty computations and allows users to trade their excess electricity among themselves. The bid selection and calculation of the trading price are performed in a decentralised and oblivious manner. The billing protocol is based on a simple privacy-friendly aggregation technique that allows suppliers to compute their customers' monthly bills without learning their fine-grained electricity consumption data. We also implemented and tested the performance of the trading protocol with realistic data. Our results show that it can be performed for 2500 bids in less than five minutes in the on-line phase, showing its feasibility for a typical electricity trading period of 30 minutes.

Mustafa A. Mustafa, Sara Cleemput, Abelrahaman Aly et al.

In this paper we propose a novel protocol that allows suppliers and grid operators to collect users' aggregate metering data in a secure and privacy-preserving manner. We use secure multiparty computation to ensure privacy protection. In addition, we propose three different data aggregation algorithms that offer different balances between privacy-protection and performance. Our protocol is designed for a realistic scenario in which the data need to be sent to different parties, such as grid operators and suppliers. Furthermore, it facilitates an accurate calculation of transmission, distribution and grid balancing fees in a privacy-preserving manner. We also present a security analysis and a performance evaluation of our protocol based on well known multiparty computation algorithms implemented in C++.