Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Documenti analoghi

• Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs
  di: Rando, Javier, et al.
  Pubblicazione: (2024)
• JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
  di: Chao, Patrick, et al.
  Pubblicazione: (2024)
• Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
  di: Terekhov, Mikhail, et al.
  Pubblicazione: (2025)
• Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs
  di: Panfilov, Alexander, et al.
  Pubblicazione: (2026)
• Is In-Context Learning Sufficient for Instruction Following in LLMs?
  di: Zhao, Hao, et al.
  Pubblicazione: (2024)