Mitigating Malicious Attacks in Federated Learning via Confidence-aware Defense
This addresses security issues in distributed machine learning for applications like healthcare or finance, but it is incremental as it builds on existing defense methods by improving detection against unseen attacks.
The paper tackles the vulnerability of Federated Learning systems to data and model poisoning attacks by proposing a Confidence-Aware Defense framework that uses confidence scores to detect malicious clients, resulting in significantly enhanced robustness and higher model accuracy across various attack scenarios.
Federated Learning (FL) is a distributed machine learning diagram that enables multiple clients to collaboratively train a global model without sharing their private local data. However, FL systems are vulnerable to attacks that are happening in malicious clients through data poisoning and model poisoning, which can deteriorate the performance of aggregated global model. Existing defense methods typically focus on mitigating specific types of poisoning and are often ineffective against unseen types of attack. These methods also assume an attack happened moderately while is not always holds true in real. Consequently, these methods can significantly fail in terms of accuracy and robustness when detecting and addressing updates from attacked malicious clients. To overcome these challenges, in this work, we propose a simple yet effective framework to detect malicious clients, namely Confidence-Aware Defense (CAD), that utilizes the confidence scores of local models as criteria to evaluate the reliability of local updates. Our key insight is that malicious attacks, regardless of attack type, will cause the model to deviate from its previous state, thus leading to increased uncertainty when making predictions. Therefore, CAD is comprehensively effective for both model poisoning and data poisoning attacks by accurately identifying and mitigating potential malicious updates, even under varying degrees of attacks and data heterogeneity. Experimental results demonstrate that our method significantly enhances the robustness of FL systems against various types of attacks across various scenarios by achieving higher model accuracy and stability.