Investigating the Factors Impacting Adversarial Attack and Defense Performances in Federated Learning
Authors:
- Nura AljaafariNANura Aljaafari
- Mahmoud NazzalMahmoud Nazzal
- Ahmad H. SawalmehAhmad H. Sawalmeh
- Abdallah KhreishahAKAbdallah Khreishah
- Muhammad AnanMAMuhammad Anan
- Abdulelah AlgosaibiAAAbdulelah Algosaibi
- Mohammed Abdulaziz AlnaeemMAMohammed Abdulaziz Alnaeem
- Adel AldalbahiAAAdel Aldalbahi
- Abdulaziz AlhumamAAAbdulaziz Alhumam
- Conrado P. VizcarraCVConrado P. Vizcarra
- 18 May 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Engineering Management
- Vol. 71 (00189391) , 12542-12555
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.Keywords
Funding Information
- Deputyship for Research and Innovation, Ministry of Education, Saudi Arabia (1120)
This publication has 28 references indexed in Scilit:
- Federated Learning: Challenges, Methods, and Future DirectionsIEEE Signal Processing Magazine, 2020
- FedHealth: A Federated Transfer Learning Framework for Wearable HealthcareIEEE Intelligent Systems, 2020
- Federated Learning in Mobile Edge Networks: A Comprehensive SurveyIEEE Communications Surveys & Tutorials, 2020
- PDGAN: A Novel Poisoning Defense Method in Federated Learning Using Generative Adversarial Network2020
- A Backdoor Attack Against LSTM-Based Text Classification SystemsIEEE Access, 2019
- Poisoning Attack in Federated Learning using Generative Adversarial Nets2019
- Certified Robustness to Adversarial Examples with Differential Privacy2019
- Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning2019
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004