Siyuan Liang

Beacon: Thwarting Backdoor Attacks in Cross-Domain Federated Fine-Tuning via Gradient Behavior Decoupling

RobustIT: Adapter-Centric and Attack-Agnostic Anti-Backdoor Instruction Tuning

Auditing Test Data Contamination with Error Rate Control for Reliable LLM Evaluation

Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing

T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks

Lie Detector: Unified Backdoor Detection via Cross-Examination Framework

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks

NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models

CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning

No Access, No Safety: Free Lunch Adversarial Attacks on Black-box NLP Models