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.
提出 Tracekit，审计编码 Agent 的意图、推理与动作并检测账本篡改
Published Sep 29
Evaluated models Claude Code (claude -p, version 2.1) , 独立评审（同一 CLI，无工具） Abstract Tracekit 把意图、自述和动作写入可锚定的哈希链。Tracekit 是无第三方依赖的编码智能体审计层：把人类请求、模型自述和已执行动作并排写入可外部锚定的哈希链，执行前用正则门，事后用规则和独立模型互查。
构建支付欺诈基准 ACB，评测花钱智能体的欺诈检测
Published Sep 27
Evaluated models gordonguard , pattern judge Abstract ACB 把支付欺诈与智能体操纵分开测量，作者强调观察权限、误报预算和微支付复核成本。ACB 是一套智能体支付欺诈基准与检测参考栈 ，目标是衡量钱是否被不当提取，而不仅是智能体是否接受了恶意指令。
提出 S³，用 guard agent 编排阶段安全技能防御智能体多阶段风险
Published Aug 3
Evaluated models DeepSeek-V4-Pro , DeepSeek-V4-Flash 提出 Janus 前瞻守卫，在长程智能体执行有害动作前拦截潜在风险
Published Jul 22
Evaluated models Vanguard 提出进程外双通道对比分类，拦截计算机使用智能体的错误点击
Published Mar 16
Evaluated models multi-modal-embed-small Abstract 感知错误可被屏幕像素对调利用。作者把 CUA 的感知失败写成安全漏洞visual confused deputy ：智能体按看错的屏幕授权 click(x,y)，真实落点与它以为的元素不一致。
提出 OpenSec，评测事件响应 Agent 在对抗证据下的遏制校准
Published Jan 29
Evaluated models GPT-5.2 , Claude Sonnet 4.5 , Gemini 3 and others5 Abstract OpenSec 以执行评分测 IR 智能体在对抗证据下是否过度遏制，作者称缺口在克制。OpenSec 用 dual-control 事件环境测量 IR 智能体在对抗证据下的校准：分数看实际遏制，不看报告文本。
You have reached the end