Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 265 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.
用配对回放评测任务范围授权能否阻断越权工具执行
Published Oct 5
Evaluated models Llama 3.2 3B Instruct Q4 K M , Qwen3 4B Instruct , Gemma 3 4B and others8 提出 ToolFence，以能力蓝图和确定性授权拦截 Agent 未授权工具调用
Published Sep 29
Evaluated models Qwen3-max , GPT-4o (gpt-4o-2024-08-06) , Mistral-Small-3.1-24B-Instruct-2503 提出多源完整性认证器，在结构化 Agent 动作执行前按控制域决定准入或弃权
Published Sep 28
Evaluated models Claude Opus 4.8 , GPT-5.5 , Gemini 3.1 Pro and others5 Abstract 作者给出条件性的动作完整性认证。这是一项结构化动作执行前的完整性防御研究 ，对象是从可腐化文档和工具输出拼装的支付等特权动作。
用任务绑定令牌和策略预言机拦住多智能体流水线的未授权执行
Published Sep 15
Evaluated models gemma4:31b-cloud Abstract 结构性授权拦住了记忆投毒的未授权执行，持密钥时承重的是策略预言机。作者在一条会改写沙箱邮件库的四智能体流水线上，检查低权限失陷会不会变成未授权的真实动作。
You have reached the end