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
21.05.2026
Björn Eskofier Featured in Heise Online
Björn Eskofier participated in the panel discussion “How Research Scientists Build Health AI” at the Digital Health Innovation Forum.
11.05.2026
Cordelia Schmid Featured in Süddeutsche Zeitung
Cordelia Schmid, a member of the MCML Advisory Board, was recently featured in Süddeutsche Zeitung for her work in computer vision and robotics.
08.05.2026
Right Answer, Wrong Reasoning - Is AI Thinking or Cheating?
Can AI cheat without us noticing? Our PI Barbara Plank and her team introduce a new detection method at ICLR 2026.
