Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing

Ähnliche Einträge

• Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models
  von: Zhao, Wei, et al.
  Veröffentlicht: (2024)
• Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing
  von: Zhao, Yinzhi, et al.
  Veröffentlicht: (2026)
• SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
  von: Robey, Alexander, et al.
  Veröffentlicht: (2023)
• Do Influence Functions Work on Large Language Models?
  von: Li, Zhe, et al.
  Veröffentlicht: (2024)
• Q-MLLM: Vector Quantization for Robust Multimodal Large Language Model Security
  von: Zhao, Wei, et al.
  Veröffentlicht: (2025)