Siyuan Liang
~Siyuan_Liang1
11
论文总数
5.5
年均投稿
平均评分
接收情况8/11
会议分布
ICLR
6
NeurIPS
4
ICML
1
发表论文 (11 篇)
20257 篇
4
No Access, No Safety: Free Lunch Adversarial Attacks on Black-box NLP Models
ICLR 2025withdrawn
3
NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models
ICLR 2025Poster
4
CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning
ICLR 2025withdrawn
4
T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks
NeurIPS 2025Poster
4
Lie Detector: Unified Backdoor Detection via Cross-Examination Framework
NeurIPS 2025Poster
3
ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks
ICML 2025Poster
4
Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing
NeurIPS 2025Poster
20244 篇
4
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
NeurIPS 2024Poster
3
Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
ICLR 2024Spotlight
4
Less is More: Fewer Interpretable Region via Submodular Subset Selection
ICLR 2024Oral
4
Adversarial Instance Attacks for Interactions between Human and Object
ICLR 2024Rejected