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
20.03.2026
MCML Reaches H-Index of 100
MCML reaches an h-index of 100, marking a milestone achieved through years of collaboration with LMU Munich, TUM, and research partners worldwide.
19.03.2026
Teaching Models to Say ‘I’m Not Sure’
Unified diffusion theory for images and text, bridging continuous and discrete models in one clear framework for generative AI.
12.03.2026
Frauke Kreuter becomes AAAS Fellow
MCML PI Frauke Kreuter has been elected a Fellow of the American Association for the Advancement of Science (AAAS).
