Ting Wang

Self-Destructive Language Models

Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models

Self-Improving Model Steering

AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models

MEDMKG: Benchmarking Medical Knowledge Exploitation with Multimodal Knowledge Graph

Safeguarding Vision-Language Models via Dynamic Token Reweighting

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction

RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models

Securing Multimodal Large Language Models: Defending Against Jailbreak Attacks with Adversarial Tuning

Your Agent Can Defend Itself against Backdoor Attacks