Sheng Liu

FedTrident proposes a comprehensive framework to defend Federated Learning-based Road Condition Classification against Targeted Label-Flipping Attacks, achieving robust performance comparable to non-attack scenarios.

DEMUX is a novel framework that addresses the challenge of multi-tab website fingerprinting by treating the interleaved traffic as a demixing problem, achieving state-of-the-art performance in complex scenarios.

SafeSteer proposes a localized on-policy distillation method that restricts safety alignment to specific safety tokens, thereby achieving strong safety performance with minimal degradation to general capabilities and significantly reducing data requirements.