Hidden in Thought: Transferable Chain-of-Thought Artifacts Induce Harmful Behavior
英文标题：Hidden in Thought: Transferable Chain-of-Thought Artifacts Induce Harmful Behavior
arXiv:2607.15286v1 Announce Type: cross Abstract: We investigate whether harmful chain-of-thought (CoT) traces from compromised language models can transfer unsafe behaviour and be distilled into reusable jailbreak attacks. Using an emergent-misalignment organism and a refusal-ablated jailbroken or
打开原文相关 1.6 · 机会 2
2.1 KB
640 B
612 B
380 B
9.1 KB
32.7 KB
22.8 KB
24.2 KB
34.7 KB
中文
arXiv:2607.15286v1 Announce Type: cross Abstract: We investigate whether harmful chain-of-thought (CoT) traces from compromised language models can transfer unsafe behaviour and be distilled into reusable jailbreak attacks. Using an emergent-misalignment organism and a refusal-ablated jailbroken or
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
BibTeX formatted citation
×