Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 232 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.
测量事实核查评测混入的时序证据与参数泄漏
Published Oct 4
Evaluated models Qwen3-14B , phi-4 Abstract 两条后见通道会抬高事实核查分数。作者量的是 LLM 事实核查分数里，有多少来自 claim 当时还不可知的信息。通道有两条：预训练记住的结局，以及检索到的、写于 claim 之后的文档。
提出竞争风险模型系统化自主 Agent 失控并审计事件与评测
Published Sep 30 Abstract 竞争风险框架把完成、停止与逃逸放在同一预算上，审计显示现有记录不足以估计该过程。
用五阶段蒙特卡洛分析奖励作弊如何导致 Agent 围堵失效
Published Sep 26 Abstract 分层控制的模拟事件率低于弱控制以及单独隔离或单独监控。这项研究用蒙特卡洛把奖励黑客接到外部安全事件上，比较的是控制组合，不是 Hugging Face 事件的再现概率。
归纳开放式医学长答案检索核验的失败分类
Published Sep 25
Evaluated models GPT-5.4 , Mistral Small 3 (24B-Instruct-2501) , Mistral Small 4 (119B-2603) and others8 Abstract 作者把开放式低召回归为证据是否在库、能否被定位，以及与声明是否对齐。这篇工作诊断开放式医学事实核验的 retrieve-then-verify 管线断在哪里，而不是提出新的核验器。
提出 Trace2ATT&CK，用溯源图把内核遥测映射到 ATT&CK
Published Sep 11
Evaluated models gpt-oss-20b , gpt-oss-120b , gemma-4-31b-it and others7 Abstract Trace2ATT&CK 把 eBPF 溯源命令图交给本地 LLM/RAG，在 Atomic Red Team 上映射 ATT&CK。Trace2ATT&CK 是一条从 Linux 内核遥测到 MITRE ATT&CK 排序候选的端到端流水线，面向已经划定的攻击窗口，而不是异常检测或 CTI 报告。
用 Tamarin 形式化分析智能体支付协议的跨阶段安全关系
Published Aug 30
Evaluated models x402 , MPP , ACP and others4 You have reached the end