Boheng Li

Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning

OASIS: One-Shot Federated Graph Learning via Wasserstein Assisted Knowledge Integration

Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack

Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes