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.
Proposes LGWM, using an action-conditioned world model to verify GUI agent screen transitions.
Published Oct 8
Evaluated models LGWM AI summary 研究者提出一种轻量级路由 logits 安全检测器,在提示词预填充阶段读取 MoE 视觉语言模型的专家路由信号,在生成前判断多模态请求是否安全,且不修改模型参数或专家路由。
Published Oct 6
Evaluated models Qwen3-VL-30B-A3B-Instruct , Kimi-VL-A3B-Instruct Abstract 读出而非操纵 router logits,可在不改模型的情况下降低两模型的组合式安全错误。作者在两个指令微调 MoE VLM 上比较改模型与读路由。组合式风险按 HoliSafe 分成五类:图文各自可安全,合在一起才不安全,或不安全内容只在图像里。
提出条件特征抑制防御,检出对抗补丁后抑制 VLA 内部特征
Published Oct 2
Evaluated models π0.5 , SmolVLA Abstract 条件抑制与 patch 相关的 SAE 特征,间歇攻击下可提高 SR,持续攻击下则不能。
系统评估循环语言模型加深 loop 后的 CoT 可监控性
Published Oct 2
Evaluated models Ouro-1.4B-Thinking , Ouro-2.6B-Thinking , Nanbeige4.2-3B and others4 Abstract 加深 loop 可在部分压力测试任务降低可监测性,循环架构本身并不必然更难监测。这项工作评估 LoopLM 的 CoT 可监测性:加深共享层的重复次数,以及“有循环结构”本身,会不会让决策关键因素更少出现在可监测文本里。
提出 NDDL,用良性扩散轨迹检测文生图后门提示并定位触发 token
Published Sep 30
Evaluated models Stable Diffusion v1.5 , Stable Diffusion XL , Stable Diffusion v3.5 and others4 Abstract NDDL 从良性扩散轨迹学习正常转移,用动态不一致检测后门并定位触发 token。NDDL 是面向文生图扩散模型的后门防御:防御者只有白盒模型访问和良性提示词,没有后门先验,需要区分后门提示词并找出触发 token。
分析隐蔽推理在思维链监控下的信息足迹下界与不可读性
Published Sep 29
Evaluated models Qwen2.5-7B-Instruct , Llama-3.1-8B-Instruct , Qwen 3.5 397B-A17B and others12 Abstract 论文从理论与实证探明了思维链监控的边界:复杂隐蔽计算必然泄露信息足迹且需承担长度税,但该足迹可被在线加密而不可读。
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。
提出 VisER,用内部视觉证据检测 LVLM 物体幻觉
Published Aug 31
Evaluated models LLaVA-1.5-7B , LLaVA-NeXT-7B , InstructBLIP and others8 Abstract VisER 用证据门与图像–前缀比给物体提及打落地分。VisER 是面向 LVLM 开放式图像描述的免训练物体级幻觉检测分数,用来处理内部支持的来源混淆。
提出 INTENT-AS-A-TOOL,用意图工具概率跟踪并干预智能体失准
Published Aug 28
Evaluated models Gemma-4-31B-IT , Qwen3.5-27B , Qwen3-235B-A22B and others5 Abstract 用意图工具的下一动作概率跟踪推理中的失准承诺,并在其成为首选时插入反思。Zhang 等人研究推理型语言模型在职场邮件沙箱里如何走向智能体失准,并提出用动作偏好而不是事后文本标签来跟踪承诺。问题是:有害执行往往出现在推理已经形成意图之后,但 CoT 监控是事后、粗粒度、依赖外部评审的,也看不到模型倾向调用哪个动作。
You have reached the end