382 citations · 2.5k across the 96 of their papers we have counts for
3 papers · 2 filters
Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine Learning
Jiachen T. Wang, Saeed Mahloujifar, Shouda Wang +2
Propose-Test-Release (PTR) is a differential privacy framework that works with local sensitivity of functions, instead of their global sensitivity. This framework is typically used…
Neurotoxin: Durable Backdoors in Federated Learning
Zhengming Zhang, Ashwinee Panda, Linyue Song +5
Due to their decentralized nature, federated learning (FL) systems have an inherent vulnerability during their training to adversarial backdoor attacks. In this type of attack, the…
Leveraging strategic connection migration-powered traffic splitting for privacy
Mona Wang, Anunay Kulshrestha, Liang Wang +1
Network-level adversaries have developed increasingly sophisticated techniques to surveil and control users' network traffic. In this paper, we exploit our observation that many en…