Nuclear Deployed: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents

Documenti analoghi

• How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
  di: Zhou, Zhenhong, et al.
  Pubblicazione: (2024)
• The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation
  di: Xu, Rongwu, et al.
  Pubblicazione: (2023)
• Preemptive Answer "Attacks" on Chain-of-Thought Reasoning
  di: Xu, Rongwu, et al.
  Pubblicazione: (2024)
• A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy
  di: Wang, Huandong, et al.
  Pubblicazione: (2025)
• How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?
  di: Li, Yuxuan, et al.
  Pubblicazione: (2026)