Perception Poisoning Attacks in Federated Learning
Ka-Ho Chow, Ling Liu · 2021
Federated learning (FL) enables decentralized training of deep neural networks (DNNs) for object detection over a distributed population of clients. It allows edge clients to keep their data local and only share parameter updates with a federated server. However, the distributed nature of FL also opens doors to new threats. In this paper, we present targeted perception poisoning attacks against federated object detection learning in which a subset of malicious clients seeks to poison the federated training of a global object detection model by sharing perception-poisoned local model parameters. We first introduce three targeted perception poisoning attacks, which have severe adverse effects only on the objects under attack. We then analyze the attack feasibility, the impact of malicious client availability, and attack timing. To safeguard FL systems against such contagious threats, we introduce spatial signature analysis as a defense to separate benign local model parameters from poisoned local model contributions, identify malicious clients, and eliminate their impact on the federated training. Extensive experiments on object detection benchmark datasets validate that the defense-empowered federated object detection learning can improve the robustness against all three types of perception poisoning attacks. The source code is available at https://github.com/git-disl/Perception-Poisoning.