Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 13 papers 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.
提出 Inspect Robots,在真实机器人上评测具身模型的能力与拒答
Published Oct 5
Evaluated models Astra(GPT-6 Astra) , GPT-6 Sol , GPT-5.6 Sol and others7 提出危害窗口与区间指标,统一评测分解攻击和提示注入下的智能体滥用监视
Published Oct 5
Evaluated models Gemma 4 26B-A4B , Qwen3.6 27B , Qwen3.5 27B and others12 Abstract 统一智能体滥用监视框架,动作视角兼顾两类威胁但危害定位仍存瓶颈。
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。
提出 Persona Guardrail,强制客服智能体守住功能边界
Published Oct 2
Evaluated models Qwen3-30B-A3B , Qwen3-VL-30B , Qwen3-8B and others5 Abstract Persona Guardrail 用功能边界做同步输入输出校验,并在 PAGE 与生产延迟预算下给出评测。Persona Guardrail 是客服向智能体的同步运行时防御:先写明功能边界,再决定放行或拦截,而不是只检测某一攻击类。
提出闭环自适应红队框架 CART,评测模型与 Agent 的安全失败
Published Sep 23
Evaluated models Claude Opus 4.8 , GPT-5.5 , Grok 4.3 and others7 Abstract CART 把红队做成可审计的闭环搜索,在三类评测上比静态回放发现更多失败与更高平均风险。CART 把自动红队从一次清单式打分,改成带预算、可追溯的闭环搜索。
提出 CS-Guard 基准,评测代码生成护栏对虚构场景攻击的防御
Published Sep 9
Evaluated models CodeLlama-13B-Instruct , DeepSeekCoder-V2-Lite-16B , GPT-OSS-20B and others7 Abstract 论文提出了代码安全护栏基准 CS-Guard,评估发现现有护栏对虚构场景攻击和代码级恶意请求防御较弱。
构建 SciHazard 基准,评测科研智能体与 LLM 的科学危险能力
Published Jul 21
Evaluated models WebThinker + DeepSeek-R1 , InternAgent , Gemini Deep Research and others19 Abstract SciHazard 用分解评分测科学滥用风险,作者称智能体抬高了可执行危害。SciHazard 是一个科学滥用风险基准,配一个把危害拆开再合成的自动分数。
用对抗提示审计安全代码生成方法在自然语言改写后的安全与功能
Published Jan 12
Evaluated models Salesforce/codegen-350M-multi , codegen-2B-multi , codegen-6B-multi and others5 提出多轮在线骚扰 Agent 基准,评测记忆、规划与微调越狱
Published Oct 16, 2025
Evaluated models LLaMA-3.1-8B-Instruct , Qwen3-30B-A3B-Instruct , DeepSeekMoE-16B and others4 提出 JAWS-Bench,评测代码 Agent 在三级工作区中的越狱与恶意代码可执行性
Published Oct 2, 2025
Evaluated models GPT-4.1 , GPT-o1 , DeepSeek-R1 and others8 Abstract 论文提出了评估代码智能体端到端恶意代码越狱的 JAWS-Bench,发现多文件与智能体推理会明显放大可部署危害。
提出 SafeScientist 四层监控,阻止科研智能体执行高风险或不伦理任务
Published May 29, 2025
Evaluated models GPT-4o , GPT-4.1 , GPT-3.5-turbo and others5 Abstract 四层监控加科研安全基准。SafeScientist 是带四层监控的科研智能体框架,并用 SciSafetyBench 评测科学场景中的任务安全。
提出 SafeArena 基准,评测网页 Agent 是否执行故意有害任务
Published Mar 7, 2025
Evaluated models GPT-4o , Claude-3.5-Sonnet , Qwen-2-VL-72B and others5 Abstract SafeArena 用配对任务和 ARIA 评测网页智能体的故意滥用。SafeArena 评测自主网页智能体是否会执行用户故意给出的恶意网页任务。 。
提出 SciGuard 外部护栏与 SciMT 基准,控制化学科学 AI 误用
Published Dec 12, 2023
Evaluated models SciGuard (GPT-4) , SciGuard (Gemini) , SciGuard (Mixtral) and others5 Abstract SciGuard 以外部智能体控制化学 AI 误用。这篇工作把化学科学 AI 的误用控制做成外部智能体,而不是改模型权重。作者担心合成规划、毒性预测和科学语言模型被用来获取有害物质信息、规避监管或传播危险知识,同时合法工业用途又不能靠一律拒绝来处理。SciGuard 由 LLM 担任中介,把原则和指南放进短期记忆,把分子库、危害库、法规和交互历史放进可检索的长期记忆,再按 Chain of Thought 调用 Chemprop、LocalRetro 等工具,或用 RAG 补法规片段,最后回答、追问或拒绝。
You have reached the end