In this thesis, we discuss a data-driven approach to defend adversarial attacks in federated learning. 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. Our aggregation strategy 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...[ Read more ]

In this thesis, we discuss a data-driven approach to defend adversarial attacks in federated learning. 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. Our aggregation strategy 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 images and text datasets.