RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion

Ähnliche Einträge

• White-box Multimodal Jailbreaks Against Large Vision-Language Models
  von: Wang, Ruofan, et al.
  Veröffentlicht: (2024)
• Simulated Ensemble Attack: Transferring Jailbreaks Across Fine-tuned Vision-Language Models
  von: Wang, Ruofan, et al.
  Veröffentlicht: (2025)
• TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models
  von: Wang, Xin, et al.
  Veröffentlicht: (2026)
• JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models
  von: Song, Jiaxin, et al.
  Veröffentlicht: (2025)
• A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Models
  von: Shuai, Xincheng, et al.
  Veröffentlicht: (2024)