Výsledky vyhledávání - "Hallaji, Ehsan"

Report

Decentralized Federated Learning: A Survey on Security and Privacy

Autor: Hallaji, Ehsan, Razavi-Far, Roozbeh, Saif, Mehrdad, Wang, Boyu, Yang, Qiang

Publikováno v: IEEE Transactions on Big Data, vol. 10, no. 2, pp. 194-213, 2024

Federated learning has been rapidly evolving and gaining popularity in recent years due to its privacy-preserving features, among other advantages. Nevertheless, the exchange of model updates and gradients in this architecture provides new attack sur

Externí odkaz: http://arxiv.org/abs/2401.17319

Zobrazit plný text záznamu

Report

Learning From High-Dimensional Cyber-Physical Data Streams for Diagnosing Faults in Smart Grids

Autor: Hassani, Hossein, Hallaji, Ehsan, Razavi-Far, Roozbeh, Saif, Mehrdad

Publikováno v: Int. J. Mach. Learn. & Cyber. (2024)

The performance of fault diagnosis systems is highly affected by data quality in cyber-physical power systems. These systems generate massive amounts of data that overburden the system with excessive computational costs. Another issue is the presence

Externí odkaz: http://arxiv.org/abs/2303.08300

Zobrazit plný text záznamu

Report

A Stream Learning Approach for Real-Time Identification of False Data Injection Attacks in Cyber-Physical Power Systems

Autor: Hallaji, Ehsan, Razavi-Far, Roozbeh, Wang, Meng, Saif, Mehrdad, Fardanesh, Bruce

Publikováno v: IEEE Transactions on Information Forensics and Security, vol. 17, pp. 3934-3945, 2022

This paper presents a novel data-driven framework to aid in system state estimation when the power system is under unobservable false data injection attacks. The proposed framework dynamically detects and classifies false data injection attacks. Then

Externí odkaz: http://arxiv.org/abs/2210.06729

Zobrazit plný text záznamu

Report

Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanisms

Autor: Hallaji, Ehsan, Razavi-Far, Roozbeh, Saif, Mehrdad

Publikováno v: Federated and Transfer Learning, Springer International Publishing, Cham, pp. 29-55, 2023

The advent of federated learning has facilitated large-scale data exchange amongst machine learning models while maintaining privacy. Despite its brief history, federated learning is rapidly evolving to make wider use more practical. One of the most

Externí odkaz: http://arxiv.org/abs/2207.02337

Zobrazit plný text záznamu