Схожие документы

• Bleeding Pathways: Vanishing Discriminability in LLM Hidden States Fuels Jailbreak Attacks
  по: Zhang, Yingjie, и др.
  Опубликовано: (2025)
• The Art of Hide and Seek: Making Pickle-Based Model Supply Chain Poisoning Stealthy Again
  по: Liu, Tong, и др.
  Опубликовано: (2025)
• Jailbreaking Large Language Models through Iterative Tool-Disguised Attacks via Reinforcement Learning
  по: Wang, Zhaoqi, и др.
  Опубликовано: (2026)
• Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models
  по: Wang, Youze, и др.
  Опубликовано: (2025)
• Demystifying RCE Vulnerabilities in LLM-Integrated Apps
  по: Liu, Tong, и др.
  Опубликовано: (2023)