Ahmad Rahdari

Smart grids combine cyber systems with complex physical networks and present numerous technological challenges. One example is the implementation of communication technology, specifically within the advanced metering infrastructure, which has made it an attractive target for attackers. Cyber attacks, such as impersonation, unauthorised data access, fraud, energy theft, and reduced network reliability, are some of the threats faced by smart grids. Notably, recent proposals by Mahmood et al., Braeken et al., and Chaudhry et al. aimed at establishing secure communication, claiming their methods fulfil the requisite security criteria. This paper, however, reveals that each of these proposals exhibits security vulnerabilities and lacks sufficient features for deployment. In response to these shortcomings, this paper introduces a novel elliptic curve cryptography‐based key establishment scheme, specifically designed to enhance communication security in smart grid cyber‐physical systems. A comprehensive and comparative analysis of the security attributes of the proposed scheme is presented. Furthermore, the security of the scheme is formally validated within the random oracle under the Canetti‐Krawczyk security model. The AVISPA tool is also leveraged to verify the security assertions. The findings demonstrate that the proposed protocol is pioneering in efficiently satisfying the non‐repudiation feature, simultaneously ensuring user anonymity and perfect forward secrecy. It exhibits robustness against various well‐known attacks, including Denial of Service and ephemeral secret leakage attacks, all while effectively managing both computational complexity and communication costs.

Machine learning and deep learning are transformative forces reshaping our networks, industries, services, and ways of life. However, the susceptibility of these intelligent systems to adversarial attacks remains a significant issue. On the one hand, recent studies have demonstrated the potential transferability of adversarial attacks across diverse models. On the other hand, existing defense mechanisms are vulnerable to advanced attacks or are often limited to certain attack types. This study proposes a random deep feature selection approach to mitigate such transferability and improve the robustness of models against adversarial manipulations. Our approach is designed to strengthen deep models against poisoning (e.g., label flipping) and exploratory (e.g., DeepFool, BIM, FGSM, I-FGSM, L-BFGS, C&W, JSMA, and PGD) attacks that are applied in both the training and testing stages, and Transfer Learning-Based Adversarial Attacks. We consider scenarios involving perfect and semi-knowledgeable attackers. The performance of our approach is evaluated through extensive experiments on the renowned UNSW-NB15 dataset, including both real-world and synthetic data, covering a wide range of modern attack behaviors and benign activities. The results indicate that our approach boosts the effectiveness of the target network to over 80% against labelflipping poisoning attacks and over 60% against all major types of exploratory attacks.

The increasing need to process large, high-dimensional datasets and the substantial computational power required have made the use of distributed cloud servers essential. These servers provide cost-effective solutions that make storage and computing accessible to ordinary users. However, they might face significant vulnerabilities, including data leakage, metadata spoofing, insecure programming interfaces, malicious insiders, and denial of service. To gain public trust in distributed computing, addressing concerns related to privacy and security while ensuring high performance and efficiency is crucial. Multiparty computation, differential privacy, trusted execution environments, and federated learning are the four major approaches developed to address these issues. This survey paper reviews and compares these four approaches based on a structured framework, by highlighting recent top-tier research papers published in prestigious journals and conferences. Particular attention is given to progress in federated learning, which trains a model across multiple devices without sharing the actual data, keeping data private and secure. The survey also highlights federated learning techniques, including secure federated learning, by detecting malicious updates and privacy-preserving federated learning via data encryption, data perturbation, and anonymization, as new paradigms for building responsible computing systems. Finally, the survey discusses future research directions for connecting academic innovations with real-world industrial applications.