Схожие документы

• IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves
  по: Wang, Ruofan, и др.
  Опубликовано: (2024)
• RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion
  по: Wang, Ruofan, и др.
  Опубликовано: (2025)
• White-box Multimodal Jailbreaks Against Large Vision-Language Models
  по: Wang, Ruofan, и др.
  Опубликовано: (2024)
• Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
  по: Cui, Kaiyuan, и др.
  Опубликовано: (2026)
• BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
  по: Li, Juncheng, и др.
  Опубликовано: (2025)