Defense Strategies Toward Model Poisoning Attacks in Federated Learning: A Survey

02/13/2022

∙

Advances in distributed machine learning can empower future communications and networking. The emergence of federated learning (FL) has provided an efficient framework for distributed machine learning, which, however, still faces many security challenges. Among them, model poisoning attacks have a significant impact on the security and performance of FL. Given that there have been many studies focusing on defending against model poisoning attacks, it is necessary to survey the existing work and provide insights to inspire future research. In this paper, we first classify defense mechanisms for model poisoning attacks into two categories: evaluation methods for local model updates and aggregation methods for the global model. Then, we analyze some of the existing defense strategies in detail. We also discuss some potential challenges and future research directions. To the best of our knowledge, we are the first to survey defense methods for model poisoning attacks in FL.

READ FULL TEXT

Defense Strategies Toward Model Poisoning Attacks in Federated Learning: A Survey

Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions

Challenges and approaches for mitigating byzantine attacks in federated learning

Revisiting Personalized Federated Learning: Robustness Against Backdoor Attacks

Backdoor Attacks against Voice Recognition Systems: A Survey

FedMLSecurity: A Benchmark for Attacks and Defenses in Federated Learning and LLMs

Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directions

Cybersecurity Threats in Connected and Automated Vehicles based Federated Learning Systems

Defense Strategies Toward Model Poisoning Attacks in Federated Learning: A Survey

Related Research

Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions

Challenges and approaches for mitigating byzantine attacks in federated learning

Revisiting Personalized Federated Learning: Robustness Against Backdoor Attacks

Backdoor Attacks against Voice Recognition Systems: A Survey

FedMLSecurity: A Benchmark for Attacks and Defenses in Federated Learning and LLMs

Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directions

Cybersecurity Threats in Connected and Automated Vehicles based Federated Learning Systems