Zhibo Wang

A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectives

2023 · arXiv (Cornell University)

Backdoor attacks pose serious security threats to deep neural networks (DNNs). Backdoored models make arbitrarily (targeted) incorrect predictions on inputs embedded with well-designed triggers while behaving normally on clean inputs. Many works have explored the …

Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learning

2024 · arXiv (Cornell University)

Federated Learning (FL) exhibits privacy vulnerabilities under gradient inversion attacks (GIAs), which can extract private information from individual gradients. To enhance privacy, FL incorporates Secure Aggregation (SA) to prevent the server from obtaining individual gradients, …