Jiongxiao Wang

Robust Representation Consistency Model via Contrastive Denoising

Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset

Prompt Injection Benchmark for Foundation Model Integrated Systems

BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment

Conversational Drug Editing Using Retrieval and Domain Feedback

Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness