Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 233 papers do not have category tags yet and are not included in filtered results.
“
About this collection Collection in progress We are building a large AI safety paper collection to help researchers find work related to their interests. Papers are collected automatically andfiltered only for relevance to AI safety , without judging quality, novelty or reading value. The default “Annotated first” shows papers with tags or published paper analyses first. Each group is ordered by original publication date, newest first, with undated papers last. “Newest first” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and paper analyses are prepared by AI from the papers. Language models may have systematic biases and produce hallucinations.We plan to carry out human annotation and review to reduce errors in this content.
提出 SLDR，用选择性层恢复与动态路由防御恶意微调
Published Oct 8
Evaluated models Llama3.1-8B-Instruct , Llama3-8B-Instruct , Qwen2.5-7B-Instruct and others4 Abstract 作者称 SLDR 能压低有害输出并保持下游效用。SLDR 是针对恶意微调的微调后防御：在已对齐模型上做有符号层探测，只在敏感分数最大与最小的两层训练 LoRA，再用 lmax 的最后 token 表示决定是否启用适配器。
提出 ASA 与 AttestMCP，度量并降低 LLM 对输入序列扰动的敏感
Published Oct 2
Evaluated models Gemma-3-27B-Instruct , Gemma-3-4B-Instruct , Llama-3.2-3B-Instruct and others12 提出主题锚点投毒，放大众包微调后的专有指令提取
Published Sep 28
Evaluated models Qwen2.5-7B-Instruct , Qwen2.5-14B-Instruct , Llama-3.1-8B-Instruct and others4 Abstract 论文提出基于主题锚点的数据中毒攻击，证明低比例的中毒样本可在黑盒条件下隐蔽放大微调指令泄漏。
提出 SEAL，在 MoE 共享专家上做 DPO-LoRA 对齐以抵御越狱与权重篡改
Published Sep 2
Evaluated models Qwen1.5-MoE-A2.7B , DeepSeekMoE-16B , GLM-4.7-Flash and others4 Abstract SEAL 把 DPO-LoRA 限制在混合 MoE 共享专家上，SEAL++再保护已有安全神经元方向。SEAL 是面向混合 MoE 的训练时防御：只对齐始终执行的共享专家，使安全不依赖路由器是否把 token 送到安全专家。
提出 ColluSkill，用跨技能组合绕过 Agent 技能扫描器
Published Aug 10
Evaluated models GPT-5.5 , DeepSeek-V4-Pro , GLM-5.2 Abstract 论文揭示了单技能孤立扫描的盲区，提出多技能链攻击 ColluSkill 与上下文防御 ChainGuard 并验证了有效性。
提出 iMIST，用工具伪装和 PPO 迭代越狱大语言模型
Published Jan 9
Evaluated models DeepSeek-V3 , Qwen3-32B , GPT-OSS-120B Abstract iMIST 用工具伪装和在线 PPO 做黑盒越狱，Table I 中 JADES 高于同格基线。iMIST 是黑盒越狱方法：把恶意查询伪装成合法工具调用，再用在线强化学习把响应的有害性分数往上推。
You have reached the end