Federated Learning

Chapter 9: Meta-federated learning

Omid Aramoon^a; Pin-Yu Chen^b; Gang Qu^a; Yuan Tian^c    aUniversity of Maryland at College Park, College Park, MD, United States^bIBM Research, Yorktown Heights, NY, United States^cUniversity of Virginia, Charlottesville, VA, United States

Abstract

Due to its distributed methodology alongside its privacy-preserving features, Federated learning (FL) is vulnerable to training time adversarial attacks. In this study, our focus is on backdoor attacks in which the adversary's goal is to cause targeted misclassifications for inputs embedded with an adversarial trigger while maintaining an acceptable performance on the main learning task at hand. Contemporary defenses against backdoor attacks in federated learning require ...