Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 305 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 COVER，用干预门判定 Agent 规则谓词能否自动执行
Published Oct 3
Evaluated models Claude Sonnet , Claude Opus , GPT-4o and others5 Abstract 自可判定不能向模型索取。这篇工作测的是智能体验证器在检查之前的分流：外部规则里的哪条谓词能用固定过程解决，哪条必须交给评审。
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 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 AP2 支付协议的 Whisper 攻击与 A-VIP 绑定防御
Published Sep 11
Evaluated models gemini-2.5-flash-lite , gemini-3.1-flash-lite , gemini-3-flash-preview and others15 Abstract 论文揭示了 AP2 协议决策层受操纵的风险，提出结构化与权能绑定防御 A-VIP，并发布评测基准。
提出 Sentinel-RL，将拓扑处置从 LLM 卸载到受约束图策略
Published Sep 4
Evaluated models HetGAT , PPO Abstract Sentinel-RL 用图编码器与 PPO 承担拓扑决策，LLM 负责叙述与门控，并在 LANL 上报告检测与时延。Sentinel-RL 是面向 SOC 的神经符号架构：拓扑决策离开 LLM，改由认证图上的 HetGAT 与 PPO 完成。
提出 RARE-Guard，阻止逆向观察被提升为指令或已验证声明
Published Jul 14
Evaluated models gpt-5.5 , claude-sonnet-4-6 , gemini-2.5-pro and others5 Abstract 成对二进制衡量无效提升。作者定义的失败是：LLM 辅助逆向中，忠实提取的二进制观察获得它并未赢得的指令权限、声明证据或可信状态。
You have reached the end