Jie Zhang
~Jie_Zhang14
7
论文总数
3.5
年均投稿
平均评分
接收情况4/7
会议分布
ICLR
5
ICML
2
发表论文 (7 篇)
20255 篇
4
Does Training with Synthetic Data Truly Protect Privacy?
ICLR 2025Poster
4
Blind Baselines Beat Membership Inference Attacks for Foundation Models
ICLR 2025Rejected
5
Textual Unlearning Gives a False Sense of Unlearning
ICML 2025Poster
3
The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
ICML 2025Spotlight
4
Prompt-Independent Safe Decoding to Restrain Unsafe Image Generation for Text-to-Image Models against White-Box Adversary
ICLR 2025Rejected