Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 14 papers Another 240 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.
构建 MedDistract 基准，测量偶发信息对临床文书与推理的污染
Published Oct 6
Evaluated models GPT-5.4 , GPT-5.6 Sol , Claude Opus 5 and others9 提出 RAG-PIBench，评测 RAG 上下文中提示注入检测器
Published Oct 6
Evaluated models DistilBERT-base-uncased , DeBERTa-v3-base , MiniLM 构建 AGENTDOXX 基准，评测联网搜索 Agent 对匿名访谈的再识别
Published Oct 5
Evaluated models GPT-5.6 Terra , GPT-5 Mini , GPT-4.1 Mini and others10 Abstract 论文提出了已知身份的重识别基准 AGENTDOXX，揭示搜索与记忆双重风险及现有防御在检索轨迹中的泄露漏洞。
提出 RAGStress 受控基准，评测知识库退化下的 RAG
Published Oct 4
Evaluated models Claude Sonnet 4 , Claude Opus 4.6 , DeepSeek R1 and others5 Abstract 作者用 RAGStress 比较五系统。RAGStress 是知识库损坏下的 RAG 受控压力测试。作者明确不把它当作模型排行榜。
提出面向 RAG 的证据优先发布框架 AGO，并评测评审 adherence 判别
Published Oct 1
Evaluated models gpt-4o , gpt-4.1-nano Abstract AGO 把缺失证据和评审误差写成显式发布状态，并要求按领域验证评审。AGO 是部署在企业 RAG 评估业务中的自托管发布门控，用来决定一个版本应放行、人工复核还是拦截。
提出 MADBench，评测多智能体辩论是吸收还是放大对抗影响
Published Sep 30
Evaluated models gpt-4o , GPT-5 , GPT-6 Astra Abstract MADBench 显示辩论能吸收部分准确率攻击，同时放大未授权读写。MADBench 是一个评测多智能体辩论安全性的基准，用来看攻击是被辩论吸收还是被放大。
提出 VoxParity，固定转写只改音频，评测语音智能体是否按行业规则改工具调用
Published Sep 28
Evaluated models MiMo-V2.6-Pro , gemini-3.7-flash , Qwen3.8-Omni and others15 Abstract VoxParity 用固定转写的音频对比和 words-only null，测量语音智能体是否按所听内容改变工具调用。VoxParity 测量语音智能体在词语不变、只有声音改变时，是否按行业规则改它所执行的工具调用。
评测 RAG 中过期文档推翻模型原本正确回答的现象
Published Sep 25
Evaluated models GPT-4o , GPT-4.1 , Claude-Opus-4.5 and others13 Abstract 论文评测了陈旧检索推翻正确知识的中毒现象，并分析了其内部机制与防御局限。这篇论文是对检索增强生成（RAG）中“陈旧文档中毒”现象的实证与机理评估研究。
用 MMPIBench 评测多模态提示注入对 Agent 框架的影响
Published Sep 9
Evaluated models Claude Opus 4.8 , GPT-5.4 , Gemini 3.1 Pro and others6 Abstract 论文提出 MMPIBench 评测多模态提示注入对智能体的影响，发现模型主导行为、尝试远超完成，音频通道缺乏防护。
构建 COUNTER-GEO-BENCH，评测生成式搜索中的 GEO 虚假信息防御
Published Sep 2
Evaluated models Gemma-4-31B-IT , Qwen-3.5-35B-A3B , Llama-4-Scout-17B-16E and others8 Abstract 论文构建了针对 GEO 虚假信息的首个防御基准，揭示通用护栏的失效与反作用，并提出了有效的轻量对比检测基线。
用 MisKnow-Agent 评测深度研究智能体是否采纳误导文档结论
Published Jul 23
Evaluated models DeerFlow , WebThinker , Gemini Deep Research and others6 Abstract 论文通过 MisKnow-Agent 框架评估发现长程研究智能体易采纳误导性知识，且现有防御难以完全消除该现象。
提出 PaperGuard，用图文注入与梯度扰动抬高自动审稿分数并检测恶意指令
Published Jun 11
Evaluated models Claude-sonnet-4.5 , GPT-4o , GPT-4.1 and others11 Abstract PaperGuard 测到提示注入与白盒视觉抬分，并比较分块检索防御。PaperGuard 同时评测并检测多模态 AI 审稿中的评分操纵。
测量 RAG 系统利用评测秘密抬高自动评测分数的程度
Published Jan 20 用 OpenRAG-Soc 评测社交网页 RAG 的间接提示注入与检索投毒
Published Jan 16
Evaluated models Llama-3-8B-Instruct , Mistral-7B-Instruct , Qwen2.5-14B and others8 You have reached the end