Activation Surgery: Jailbreaking White-box LLMs without Touching the Prompt

Documenti analoghi

• Predicting memorization within Large Language Models fine-tuned for classification
  di: Dentan, Jérémie, et al.
  Pubblicazione: (2024)
• Reconstructing training data from document understanding models
  di: Dentan, Jérémie, et al.
  Pubblicazione: (2024)
• RL-JACK: Reinforcement Learning-powered Black-box Jailbreaking Attack against LLMs
  di: Chen, Xuan, et al.
  Pubblicazione: (2024)
• PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage
  di: Nakka, Krishna Kanth, et al.
  Pubblicazione: (2025)
• Analysis of LLMs Against Prompt Injection and Jailbreak Attacks
  di: Jaiswal, Piyush, et al.
  Pubblicazione: (2026)