Aishan Liu

8

Papers

38

Total Citations

Papers (8)

Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift

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

NeurIPS 2025arXiv

Lie Detector: Unified Backdoor Detection via Cross-Examination Framework

Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing

NeurIPS 2025arXiv

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks

Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction

CopyrightShield: Enhancing Diffusion Model Security Against Copyright Infringement Attacks

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning