Yige Li
~Yige_Li1
9
论文总数
9.0
年均投稿
平均评分
接收情况5/9
会议分布
ICLR
6
ICML
2
NeurIPS
1
发表论文 (9 篇)
20259 篇
4
TUAP: Targeted Universal Adversarial Perturbations for CLIP
ICLR 2025Rejected
3
Detecting Backdoor Samples in Contrastive Language Image Pretraining
ICLR 2025Poster
4
X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
ICML 2025Poster
4
CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization
ICML 2025Poster
4
Do Influence Functions Work on Large Language Models?
ICLR 2025withdrawn
4
Adversarial Suffixes May Be Features Too!
ICLR 2025withdrawn
4
BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks
ICLR 2025Poster
4
Memory Injection Attacks on LLM Agents via Query-Only Interaction
NeurIPS 2025Poster
4
AnyAttack: Self-supervised Generation of Targeted Adversarial Attacks for Vision-Language Models
ICLR 2025withdrawn