Security and Privacy Issues of Federated Learning
This work addresses security and privacy issues for users and developers of Federated Learning systems, but it is incremental as it primarily categorizes existing risks without introducing new methods.
The paper tackles the security and privacy challenges in Federated Learning by presenting a comprehensive taxonomy of attacks, such as poisoning and membership inference, across various models including large language models, and proposes future research directions to fortify these systems.
Federated Learning (FL) has emerged as a promising approach to address data privacy and confidentiality concerns by allowing multiple participants to construct a shared model without centralizing sensitive data. However, this decentralized paradigm introduces new security challenges, necessitating a comprehensive identification and classification of potential risks to ensure FL's security guarantees. This paper presents a comprehensive taxonomy of security and privacy challenges in Federated Learning (FL) across various machine learning models, including large language models. We specifically categorize attacks performed by the aggregator and participants, focusing on poisoning attacks, backdoor attacks, membership inference attacks, generative adversarial network (GAN) based attacks, and differential privacy attacks. Additionally, we propose new directions for future research, seeking innovative solutions to fortify FL systems against emerging security risks and uphold sensitive data confidentiality in distributed learning environments.