Securing Federated Learning with Control-Flow Attestation: A Novel Framework for Enhanced Integrity and Resilience against Adversarial Attacks

arXiv:2403.10005v1 Announce Type: new
Abstract: The advent of Federated Learning (FL) as a distributed machine learning paradigm has introduced new cybersecurity challenges, notably adversarial attacks that threaten model integrity and participant privacy. This study proposes an innovative security framework inspired by Control-Flow Attestation (CFA) mechanisms, traditionally used in cybersecurity, to ensure software execution integrity. By integrating digital signatures and cryptographic hashing within the FL framework, we authenticate and verify the integrity of model updates across the network, effectively mitigating risks …

adversarial adversarial attacks arxiv attacks attestation challenges control cs.cr cybersecurity cybersecurity challenges distributed federated federated learning flow framework integrity machine machine learning novel paradigm privacy resilience security security framework study threaten