Translation in progress Some entries still include text in the original language.
Oct 13 · Tuesday
Another 227 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 UBA-ORL，以 BD/CM 样本在遗忘后激活离线 RL 后门
Published Sep 19
Evaluated models TD3+BC , BCQ , IQL Abstract UBA-ORL 用竞争的 BD/CM 样本，使离线 RL 后门在删除伪装轨迹后激活。UBA-ORL 研究离线强化学习中由合规轨迹删除激活的后门：合法贡献者同时上传共享触发的后门轨迹和伪装轨迹，训练后触发响应被压低，删除伪装批次后再升高。受害系统是使用静态数据集和轨迹级遗忘接口的离线 RL 服务。对手不能看到训练算法、参数、梯度或具体遗忘算法，但能提交可区分批次，并在部署时向观测注入预定触发。
提出 SKILLBLOAT，改写技能文档放大编码 Agent token 消耗
Published Aug 22
Evaluated models GLM-4.7-Flash , GLM-5 , GPT-5.4 Mini and others4 提出 CDH 攻击，让技能型 Agent 绕路放大资源消耗
Published Aug 13
Evaluated models Claude-Haiku-4.5 , DeepSeek-V4-Pro , DeepSeek-V4-Flash and others6 Abstract CDH 让静态技能在保持任务完成时拉高调用与 token，耗时则因后端而异。CDH 是针对渐进披露技能智能体的发布者侧、纯文本攻击：一个静态协调器把本可正确完成的任务，拐进有界但更耗资源的技能绕路，再交还原任务。
Propose Clawdrain, amplifying OpenClaw's token consumption with a trojan skill
Published Mar 1
Evaluated models Gemini 2.5 Pro You have reached the end