Investigating the Factors Impacting Adversarial Attack and Defense Performances in Federated Learning
Document Type
Article
Publication Date
1-1-2024
Abstract
Despite the promising success of federated learning in various application areas, its inherent vulnerability to adversarial attacks hinders its applicability in security-critical areas. This calls for developing viable defense measures against such attacks. A prerequisite for this development, however, is the understanding of what creates, promotes, and aggravates this vulnerability. To date, developing this understanding remains an outstanding gap in the literature. Accordingly, this paper presents an attempt at developing such an understanding. Primarily, this is achieved from two main perspectives. The first perspective concerns addressing the factors, elements, and parameters contributing to the vulnerability of federated learning models to adversarial attacks, their degrees of severity, and combined effects. This includes addressing diverse operating conditions, attack types and scenarios, and collaborations between attacking agents. The second perspective regards analyzing the appearance of the adversarial property of a model in how it updates its coefficients and exploiting this for defense purposes. These analyses are conducted through extensive experiments on image and text classification tasks. Simulation results reveal the importance of specific parameters and factors on the severity of this vulnerability. Besides, the proposed defense strategy is shown able to provide promising performances.
Identifier
85130497453 (Scopus)
Publication Title
IEEE Transactions on Engineering Management
External Full Text Location
https://doi.org/10.1109/TEM.2022.3155353
e-ISSN
15580040
ISSN
00189391
First Page
12542
Last Page
12555
Volume
71
Grant
1120
Fund Ref
Ministry of Education - Kingdom of Saudi Arabia
Recommended Citation
Aljaafari, Nura; Nazzal, Mahmoud; Sawalmeh, Ahmad H.; Khreishah, Abdallah; Anan, Muhammad; Algosaibi, Abdulelah; Alnaeem, Mohammed Abdulaziz; Aldalbahi, Adel; Alhumam, Abdulaziz; and Vizcarra, Conrado P., "Investigating the Factors Impacting Adversarial Attack and Defense Performances in Federated Learning" (2024). Faculty Publications. 1184.
https://digitalcommons.njit.edu/fac_pubs/1184