arXiv subjects

Mustafa A. Mustafa

Publications and source records attributed to Mustafa A. Mustafa.

At least 19 recordsLinked to original sources

arXiv2026

FedSurrogate: Backdoor Defense in Federated Learning via Layer Criticality and Surrogate Replacement

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.

cs.CR↗

arXiv2026

Privacy-Preserving Local Energy Trading Considering Network Fees

Driven by the widespread deployment of distributed energy resources, local energy markets (LEMs) have emerged as a promising approach for enabling direct trades among prosumers and consumers to balance intermittent generation and demand locally. However, LEMs involve processing sensitive participant data, which, if not protected, poses privacy risks. At the same time, since electricity is exchanged over the physical power network, market mechanisms should consider physical constraints and network-related costs. Existing work typically addresses these issues separately, either by incorporating grid-related aspects or by providing privacy protection. To address this gap, we propose a privacy-preserving protocol for LEMs, with consideration of network fees that can incite participants to respect physical limits. The protocol is based on a double-auction mechanism adapted from prior work to enable more efficient application of our privacy-preserving approach. To protect participants' data, we use secure multiparty computation. In addition, Schnorr's identification protocol is employed with multiparty verification to ensure authenticated participation without compromising privacy. We further optimise the protocol to reduce communication and round complexity. We prove that the protocol meets its security requirements and show through experimentation its feasibility at a typical LEM scale: a market with 5,000 participants can be cleared in 4.17 minutes.

cs.CR↗

arXiv2026

Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learning

Federated learning (FL) remains highly vulnerable to adaptive backdoor attacks that preserve stealth by closely imitating benign update statistics. Existing defenses predominantly rely on anomaly detection in parameter or gradient space, overlooking behavioral constraints that backdoor attacks must satisfy to ensure reliable trigger activation. These anomaly-centric methods fail against adaptive attacks that normalize update magnitudes and mimic benign statistical patterns while preserving backdoor functionality, creating a fundamental detection gap. To address this limitation, this paper introduces FeRA (Federated Representative Attention) -- a novel attention-driven defense that shifts the detection paradigm from anomaly-centric to consistency-centric analysis. FeRA exploits the intrinsic need for backdoor persistence across training rounds, identifying malicious clients through suppressed representation-space variance, an orthogonal property to traditional magnitude-based statistics. The framework conducts multi-dimensional behavioral analysis combining spectral and spatial attention, directional alignment, mutual similarity, and norm inflation across two complementary detection mechanisms: consistency analysis and norm-inflation detection. Through this mechanism, FeRA isolates malicious clients that exhibit low-variance consistency or magnitude amplification. Extensive evaluation across six datasets, nine attacks, and three model architectures under both Independent and Identically Distributed (IID) and non-IID settings confirm FeRA achieves superior backdoor mitigation. Under different non-IID settings, FeRA achieved the lowest average Backdoor Accuracy (BA), about 1.67% while maintaining high clean accuracy compared to other state-of-the-art defenses. The code is available at https://github.com/Peatech/FeRA_defense.git.

cs.LG↗

arXiv2026

Specification Vibing for Automated Program Repair

Large language model (LLM)-driven automated program repair (APR) has advanced rapidly, but most methods remain code-centric: they directly rewrite source code and thereby risk hallucinated, behaviorally inconsistent fixes. This limitation suggests the need for an alternative repair paradigm that relies on a representation more accessible to LLMs than raw code, enabling more accurate understanding, analysis, and alignment during repair. To address this gap, we propose VibeRepair, a specification-centric APR technique that treats repair as behavior-specification repair rather than ad-hoc code editing. VibeRepair first translates buggy code into a structured behavior specification that captures the program's intended runtime behavior, then infers and repairs specification misalignments, and finally synthesizes code strictly guided by the corrected behavior specification. An on-demand reasoning component enriches hard cases with program analysis and historical bug-fix evidence while controlling cost. Across Defects4J and real-world benchmarks and multiple LLMs, VibeRepair demonstrates consistently strong repair effectiveness with a significantly smaller patch space. On Defects4J v1.2, VibeRepair correctly repairs 174 bugs, exceeding the strongest state-of-the-art baseline by 28 bugs, which corresponds to a 19% improvement. On Defects4J v2.0, it repairs 178 bugs, outperforming prior approaches by 33 bugs, representing a 23% improvement. Evaluations on real-world benchmarks collected after the training period of selected LLMs further confirm its effectiveness and generalizability. By centering repair on explicit behavioral intent, VibeRepair reframes APR for the era of "vibe" coding: make the behavior sing, and the code will follow.

cs.SE↗

arXiv2025

EDGChain-E: A Decentralized Git-Based Framework for Versioning Encrypted Energy Data

This paper proposes a new decentralized framework, named EDGChain-E (Encrypted-Data-Git Chain for Energy), designed to manage version-controlled, encrypted energy data using blockchain and the InterPlanetary File System. The framework incorporates a Decentralized Autonomous Organization (DAO) to orchestrate collaborative data governance across the lifecycle of energy research and operations, such as smart grid monitoring, demand forecasting, and peer-to-peer energy trading. In EDGChain-E, initial commits capture the full encrypted datasets-such as smart meter readings or grid telemetry-while subsequent updates are tracked as encrypted Git patches, ensuring integrity, traceability, and privacy. This versioning mechanism supports secure collaboration across multiple stakeholders (e.g., utilities, researchers, regulators) without compromising sensitive or regulated information. We highlight the framework's capability to maintain FAIR-compliant (Findable, Accessible, Interoperable, Reusable) provenance of encrypted data. By embedding hash-based content identifiers in Merkle trees, the system enables transparent, auditable, and immutable tracking of data changes, thereby supporting reproducibility and trust in decentralized energy applications.

cs.DC↗

arXiv2024

Privacy-Preserving Billing for Local Energy Markets

We propose a privacy-preserving billing protocol for local energy markets (PBP-LEM) that takes into account market participants' energy volume deviations from their bids. PBP-LEM enables a group of market entities to jointly compute participants' bills in a decentralized and privacy-preserving manner without sacrificing correctness. It also mitigates risks on individuals' privacy arising from any potential internal collusion. We first propose an efficient and privacy-preserving individual billing scheme, achieving information-theoretic security, which serves as a building block. PBP-LEM utilizes this scheme, along with other techniques such as multiparty computation, inner product functional encryption and Pedersen commitments to ensure data confidentiality and accuracy. Additionally, we present three approaches, resulting in different levels of privacy protection and performance. We prove that the protocol meets its security and privacy requirements and is feasible for deployment in real LEMs: bills can be computed in less than five minutes for 4,000 users using the most computationally intensive approach, and in just 0.18 seconds using the least intensive one.

cs.CR↗

arXiv2024

Synthetic Data Aided Federated Learning Using Foundation Models

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.

cs.LG↗

arXiv2024

Proactive Load-Shaping Strategies with Privacy-Cost Trade-offs in Residential Households based on Deep Reinforcement Learning

Smart meters play a crucial role in enhancing energy management and efficiency, but they raise significant privacy concerns by potentially revealing detailed user behaviors through energy consumption patterns. Recent scholarly efforts have focused on developing battery-aided load-shaping techniques to protect user privacy while balancing costs. This paper proposes a novel deep reinforcement learning-based load-shaping algorithm (PLS-DQN) designed to protect user privacy by proactively creating artificial load signatures that mislead potential attackers. We evaluate our proposed algorithm against a non-intrusive load monitoring (NILM) adversary. The results demonstrate that our approach not only effectively conceals real energy usage patterns but also outperforms state-of-the-art methods in enhancing user privacy while maintaining cost efficiency.

eess.SY↗

arXiv2024

Efficient User-Centric Privacy-Friendly and Flexible Wearable Data Aggregation and Sharing

Wearable devices can offer services to individuals and the public. However, wearable data collected by cloud providers may pose privacy risks. To reduce these risks while maintaining full functionality, healthcare systems require solutions for privacy-friendly data processing and sharing that can accommodate three main use cases: (i) data owners requesting processing of their own data, and multiple data requesters requesting data processing of (ii) a single or (iii) multiple data owners. Existing work lacks data owner access control and does not efficiently support these cases, making them unsuitable for wearable devices. To address these limitations, we propose a novel, efficient, user-centric, privacy-friendly, and flexible data aggregation and sharing scheme, named SAMA. SAMA uses a multi-key partial homomorphic encryption scheme to allow flexibility in accommodating the aggregation of data originating from a single or multiple data owners while preserving privacy during the processing. It also uses ciphertext-policy attribute-based encryption scheme to support fine-grain sharing with multiple data requesters based on user-centric access control. Formal security analysis shows that SAMA supports data confidentiality and authorisation. SAMA has also been analysed in terms of computational and communication overheads. Our experimental results demonstrate that SAMA supports privacy-preserving flexible data aggregation more efficiently than the relevant state-of-the-art solutions.

cs.CR↗

arXiv2024

Privacy-Preserving Distributed Learning for Residential Short-Term Load Forecasting

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.

cs.LG↗

arXiv2023

A Privacy-Preserving and Accountable Billing Protocol for Peer-to-Peer Energy Trading Markets

This paper proposes a privacy-preserving and accountable billing (PA-Bill) protocol for trading in peer-to-peer energy markets, addressing situations where there may be discrepancies between the volume of energy committed and delivered. Such discrepancies can lead to challenges in providing both privacy and accountability while maintaining accurate billing. To overcome these challenges, a universal cost splitting mechanism is proposed that prioritises privacy and accountability. It leverages a homomorphic encryption cryptosystem to provide privacy and employs blockchain technology to establish accountability. A dispute resolution mechanism is also introduced to minimise the occurrence of erroneous bill calculations while ensuring accountability and non-repudiation throughout the billing process. Our evaluation demonstrates that PA-Bill offers an effective billing mechanism that maintains privacy and accountability in peer-to-peer energy markets utilising a semi-decentralised approach.

cs.CR↗

arXiv2023

QNNRepair: Quantized Neural Network Repair

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.

cs.LG↗

arXiv2023

A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation

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.

cs.AI↗

arXiv2023

Zone-Based Privacy-Preserving Billing for Local Energy Market Based on Multiparty Computation

This paper proposes a zone-based privacy-preserving billing protocol for local energy markets that takes into account energy volume deviations of market participants from their bids. Our protocol incorporates participants' locations on the grid for splitting the deviations cost. The proposed billing model employs multiparty computation so that the accurate calculation of individual bills is performed in a decentralised and privacy-preserving manner. We also present a security analysis as well as performance evaluations for different security settings. The results show superiority of the honest-majority model to the dishonest majority in terms of computational efficiency. They also show that the billing can be executed for 5000 users in less than nine seconds in the online phase for all security settings, demonstrating its feasibility to be deployed in real local energy markets.

cs.CR↗

arXiv2023

Privacy Preserving Billing in Local Energy Markets with Imperfect Bid-Offer Fulfillment (Long Version)

Smart grids are being increasingly deployed worldwide, as they constitute the electricity grid of the future, providing bidirectional communication between households. One of their main potential applications is the peer-to-peer (P2P) energy trading market, which promises users better electricity prices and higher incentives to produce renewable energy. However, most P2P markets require users to submit energy bids/offers in advance, which cannot account for unexpected surpluses of energy consumption/production. Moreover, the fine-grained metering information used in calculating and settling bills/rewards is inherently sensitive and must be protected in conformity with existing privacy regulations. To address these issues, this report proposes a novel privacy-preserving billing and settlements protocol, PPBSP, for use in local energy markets with imperfect bid-offer fulfillment, which only uses homomorphically encrypted versions of the half-hourly user consumption data. PPBSP also supports various cost-sharing mechanisms among market participants, including two new and improved methods of proportionally redistributing the cost of maintaining the balance of the grid in a fair manner. An informal privacy analysis is performed, highlighting the privacy-enhancing characteristics of the protocol, which include metering data and bill confidentiality. PPBSP is also evaluated in terms of computation cost and communication overhead, demonstrating its efficiency and feasibility for markets with varying sizes.

cs.CR↗

arXiv2023

AIREPAIR: A Repair Platform for Neural Networks

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.

cs.NE↗

arXiv2022

Combining BMC and Fuzzing Techniques for Finding Software Vulnerabilities in Concurrent Programs

Finding software vulnerabilities in concurrent programs is a challenging task due to the size of the state-space exploration, as the number of interleavings grows exponentially with the number of program threads and statements. We propose and evaluate EBF (Ensembles of Bounded Model Checking with Fuzzing) -- a technique that combines Bounded Model Checking (BMC) and Gray-Box Fuzzing (GBF) to find software vulnerabilities in concurrent programs. Since there are no publicly-available GBF tools for concurrent code, we first propose OpenGBF -- a new open-source concurrency-aware gray-box fuzzer that explores different thread schedules by instrumenting the code under test with random delays. Then, we build an ensemble of a BMC tool and OpenGBF in the following way. On the one hand, when the BMC tool in the ensemble returns a counterexample, we use it as a seed for OpenGBF, thus increasing the likelihood of executing paths guarded by complex mathematical expressions. On the other hand, we aggregate the outcomes of the BMC and GBF tools in the ensemble using a decision matrix, thus improving the accuracy of EBF. We evaluate EBF against state-of-the-art pure BMC tools and show that it can generate up to 14.9% more correct verification witnesses than the corresponding BMC tools alone. Furthermore, we demonstrate the efficacy of OpenGBF, by showing that it can find 24.2% of the vulnerabilities in our evaluation suite, while non-concurrency-aware GBF tools can only find 0.55%. Finally, thanks to our concurrency-aware OpenGBF, EBF detects a data race in the open-source wolfMqtt library and reproduces known bugs in several other real-world programs, which demonstrates its effectiveness in finding vulnerabilities in real-world software.

cs.SE↗

arXiv2022

Privacy-Friendly Peer-to-Peer Energy Trading: A Game Theoretical Approach

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.

cs.GT↗