Yong Zou
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Vision×1AI×1Crypto×1ML×1
Frequent co-authors
Research Timeline
2026
REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation Models
The paper introduces REFORGE, a black-box red-teaming framework that uses adversarial image prompts to reveal persistent vulnerabilities in current Image Generation Model Unlearning (IGMU) methods.
Highlighted terms show continued research focus across papers
Papers
cs.CVcs.AIcs.CRRecentMar 17, 2026
REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation Models
Yong Zou, Haoran Li, Fanxiao Li, Shenyang Wei +4 more
The paper introduces REFORGE, a black-box red-teaming framework that uses adversarial image prompts to reveal persistent vulnerabilities in current Image Generation Model Unlearning (IGMU) methods.
View →