13.06.2025
Volker Tresp and His Team Win ReGenAI @CVPR 2025 Best Paper Award
Honored for Work on New Jailbreak Vulnerability in T2I Diffusion Models
MCML Junior Members Tong Liu, Gengyuan Zhang, Shuo Chen, and MCML PI Volker Tresp and their co-authors have received the Best Paper Award at the Second Workshop on Responsible Generative AI (ReGenAI) Workshop at CVPR 2025 for their paper “Multimodal Pragmatic Jailbreak on Text-to-image Models”.
The authors show that text-to-image models can be easily exploited to produce unsafe content through cross‑modal interactions between safe text and images, a vulnerability that current safety filters fail to address effectively.
Congratulations from us!
Check out the full paper:
Multimodal Pragmatic Jailbreak on Text-to-image Models.
ACL 2025 - 63rd Annual Meeting of the Association for Computational Linguistics. Vienna, Austria, Jul 27-Aug 01, 2025. DOI GitHub
Related
31.07.2026
Benedikt Wiestler: We Want to Build a Time Machine
MCML PI Benedikt Wiestler explains how AI models help to develop specific strategies in clinical therapy for brain tumor patients.
28.07.2026
Gaps in the Benchmark: Why Medical AI Fails in the Real World
MCML researchers show in Nature Health how dynamic red teaming exposes hidden weaknesses in Medical AI beyond static benchmarks.
