Robust Federated Learning with Attack-Adaptive Aggregation
This addresses security issues in federated learning for applications like distributed AI, but it is incremental as it builds on existing defense strategies.
The paper tackles the vulnerability of federated learning to attacks like model poisoning and backdoor attacks by proposing an attack-adaptive aggregation strategy, achieving competitive performance in defending against these attacks on image and text datasets.
Federated learning is vulnerable to various attacks, such as model poisoning and backdoor attacks, even if some existing defense strategies are used. To address this challenge, we propose an attack-adaptive aggregation strategy to defend against various attacks for robust federated learning. The proposed approach is based on training a neural network with an attention mechanism that learns the vulnerability of federated learning models from a set of plausible attacks. To the best of our knowledge, our aggregation strategy is the first one that can be adapted to defend against various attacks in a data-driven fashion. Our approach has achieved competitive performance in defending model poisoning and backdoor attacks in federated learning tasks on image and text datasets.