Poisoning Prevention in Federated Learning and Differential Privacy via Stateful Proofs of Execution

arXiv:2404.06721v1 Announce Type: new
Abstract: The rise in IoT-driven distributed data analytics, coupled with increasing privacy concerns, has led to a demand for effective privacy-preserving and federated data collection/model training mechanisms. In response, approaches such as Federated Learning (FL) and Local Differential Privacy (LDP) have been proposed and attracted much attention over the past few years. However, they still share the common limitation of being vulnerable to poisoning attacks wherein adversaries compromising edge devices feed forged (a.k.a. poisoned) data to …

analytics arxiv collection cs.cr data data analytics data collection demand differential privacy distributed federated federated learning iot led local model training poisoning prevention privacy privacy concerns response training