Vulnerabilities of Foundation Model Integrated Federated Learning Under Adversarial Threats

arXiv:2401.10375v2 Announce Type: replace
Abstract: Federated Learning (FL) addresses critical issues in machine learning related to data privacy and security, yet suffering from data insufficiency and imbalance under certain circumstances. The emergence of foundation models (FMs) offers potential solutions to the limitations of existing FL frameworks, e.g., by generating synthetic data for model initialization. However, due to the inherent safety concerns of FMs, integrating FMs into FL could introduce new risks, which remains largely unexplored. To address this gap, we …

addresses adversarial arxiv critical cs.cr cs.dc cs.lg data data privacy federated federated learning foundation foundation models frameworks limitations machine machine learning privacy privacy and security security solutions synthetic threats under vulnerabilities