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 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 TRUSTFORK 基准，评测展示身份劫持多智能体编排权限
Published Sep 26
Evaluated models GPT-5.6-Sol , GPT-5.6-Luna , Kimi-K3 and others8 Abstract 论文提出了多智能体安全基准 TRUSTFORK，揭示展示身份如何劫持操作权威，并证明事后验证无法弥补已发生的执行破坏。
提出 AttestChain，将供应链安全智能体报告签名上链并据此控制发布
Published Sep 25
Evaluated models GPT-class LLM Abstract AttestChain 将智能体报告与链上发布门控结合，现有证据来自受控合成构建的总体结果。AttestChain 是一个把 LLM 安全检查、智能体身份验证和许可链发布策略连接起来的软件供应链防御框架。 。
提出双控多智能体基准 DUMA-Bench，测量对抗环境下的策略违反
Published Sep 21
Evaluated models GPT-5 , GPT-5-mini , GPT-5-nano and others14 Abstract DUMA-Bench 用双控交互评测智能体安全。DUMA-Bench 把 τ²-bench 的双控交互做成智能体安全评测，用来看策略违反如何随用户、模型和环境一起出现。
提出 CodePoisonRAG，对检索增强代码生成的知识库投毒以植入漏洞
Published Sep 3
Evaluated models Qwen 3.5 9B , Code Llama 13B , DeepSeek-Coder-V2 16B Abstract CodePoisonRAG 展示了 RACG 外部知识库的新攻击面，在较低投毒率下可定向诱发指定漏洞并部分抵御防御。
提出 Skill-as-API，隔离多智能体协作中的 skill 正文与系统提示词
Published Sep 1 Abstract 协议把 skill 正文留在所有者侧，四层限制发现内容、权限期限和注入拼接。Skill-as-API 是面向智能体软件工程的协调协议，用来在跨组织调用时把 skill 的代码和系统提示词留在所有者进程。作者针对三条威胁：经通道或命名空间抽取专有方法，用注入让被调用模型输出系统提示词，以及协作结束后权限继续保留。
提出分片监督，将评判标准分配给独立调用以抵御展示攻击
Published Aug 6
Evaluated models Claude Opus 4.8 , Claude Sonnet 4.6 , Claude Opus 4.6 and others4 Abstract 论文揭示决策负载是大模型监督的独立瓶颈，提出分片与辩论机制有效分离注意力与平衡证据，在多项高难度基准上实现稳健评判。本文系统研究了大语言模型在执行多标准监督与评判时的决策负载瓶颈及其安全风险。
You have reached the end