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.
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。
评测 ReAct 工具调用对多模态模型拒答有害请求的削弱
Published Oct 3
Evaluated models Gemini-2.5-Pro , Gemini-3.1-Pro-Preview , Claude Opus 4.6 and others13 Abstract 论文揭示了工具调用范式削弱 MLLM 拒答能力的现象，分析了稀释与偏移机制并验证了重注缓解方案。论文系统评估了智能体工具调用范式对多模态大语言模型拒答能力的影响，指出了工具增强视觉推理背后的安全隐患。核心探讨的问题在于：当 MLLM 从单次推理转向通过 ReAct 循环调用外部工具（打标、缩放、OCR、代码执行）时，工具使用机制本身是否会降低模型拒答有害请求的概率。
测量并预测具身 VLM 规划器的任务拒答可变性
Published Sep 30
Evaluated models gemini-robotics-er-2-preview , gemini-robotics-er-1.6-preview Abstract 日常物体能翻转一部分已给出的拒答，可翻转程度取决于任务且可被本地代理预测。作者测量 constitution 守护的具身 VLM 规划器：一次拒答在只往场景里放一个日常物体之后还保不保持得住，并把这种易翻转程度称为任务的 malleability 。
证明无显式危害的图文窄微调可诱发跨任务涌现未对齐
Published Sep 28
Evaluated models GPT-4o , GPT-4.1 , Gemini 2.5 and others15 Abstract 证实窄多模态微调可引发全面的多渠道未对齐行为转变，揭示了后训练阶段对齐被隐蔽重塑的安全隐患。论文系统探究了视觉-语言模型中由窄任务微调诱发的跨模态涌现未对齐（Emergent Misalignment, EM）现象。
提出 AV-SafetyBench 评测文生音视频模型的不安全生成
Published Sep 7
Evaluated models LTX-2.3 , Ovi-1.1 , JavisDiT++ and others7 Abstract AV-SafetyBench 用三视角评五个 T2AV 模型，显示只看视频会漏掉音频与联合风险。AV-SafetyBench 是面向文本生成音视频（T2AV）的安全基准：一条提示词同时规定画面和音频，评测同时看两轨以及它们的交互。作者要测的是，不安全含义不只出现在画面上：它可以主要由语音或声音承载，也可以只有两轨合起来才成立。T2VSafetyBench 不评音频，TTA-Bench 不评与画面的交互，作者认为二者都盖不住这些路径。
Propose the KoNA benchmark to evaluate selective non-compliance in vision-language models
Published Sep 4
Evaluated models InternVL3-2B-Instruct , InternVL3-78B-Instruct , Qwen2.5-VL-3B-Instruct and others8 Abstract KoNA evaluates selective noncompliance with five types of paired queries.KoNA is used to evaluate whether vision-language models can selectively refuse mixed queries: only handle the components that should not be followed, while answering the remaining components.
审计视觉语言模型在敏感图像上从拒答转向国家立场重构的行为
Published Aug 12
Evaluated models Qwen2-VL-7B , Qwen2.5-VL-7B , Qwen3-VL-8B and others9 Abstract 论文系统审计了 VLM 多模态审查，发现审查正从显式拒答转向隐蔽重构，且中文提示与文本先验会放大重构倾向。论文系统研究了中外开源视觉语言模型在政治敏感图像上的审查行为，主要内容如下。
提出 LABSHIELD，评测科学实验室智能体的安全推理与规划
Published Mar 12
Evaluated models GPT-5.2 , GPT-o3 , GPT-o4-mini and others20 You have reached the end