Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 39 papers Another 232 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.
Measures citation fragility in AI search, demonstrating that ordinary public posts can enter citations and answers.
Published Oct 8
Evaluated models Grok , Doubao , ChatGPT and others10 Abstract The authors claim the paper quantifies vulnerabilities in AI search caused by citation preferences and low posting thresholds; tests show public web posts can penetrate AI citations, and they call for auditing the citation supply chain.
提出流匹配逆向框架，从多向量视觉文档索引重构页面
Published Oct 7
Evaluated models Tomoro-ColQwen3-8B , ColQwen3.5-4.5B , Tomoro-colqwen3-embed-4b and others13 提出临时可见性协议，限制持续摄入 RAG 向量库的投毒暴露
Published Oct 5 Abstract 用截止期限制未核验可见时长。这篇工作给持续摄入的 RAG 向量库一个失败关闭的临时可见性协议，把协议能限制的未核验暴露和依赖检测器的中毒暴露分开。
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。
分析文本水印在 RAG 中诱发事实幻觉的机制并提出干预
Published Oct 4
Evaluated models LLaMA 3.1 8B Instruct , Mistral-7B-Instruct-v0.3 , Qwen2.5-14B-Instruct Abstract 论文揭示了生产环境文本水印导致模型事实退化的失效模式，分析了解码机制并提出针对性干预。论文研究生产级文本水印对大语言模型事实准确性的影响，分析了水印诱发幻觉的失效模式并评估了针对性缓解方案。
提出 HDI 攻击以篡改 GraphRAG 辅助结构破坏检索
Published Oct 2
Evaluated models Microsoft GraphRAG , HippoRAG2 Abstract 论文形式化了 GraphRAG 辅助模式级实体攻击面，提出 HDI 攻击并验证其攻击效果。
提出 imMRAG 攻击，从多模态 RAG 私有图像库提取内容
Published Oct 1
Evaluated models Lumina-mGPT , Gemini 2.5 Flash Image Preview , CLIP ViT-B/16 and others5 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 PILLAR，用私有词法预筛与客户端重排保护 RAG 查询
Published Sep 29 Abstract PILLAR 用固定模式的私有 BM25 预筛加本地嵌入重排，在两基准上换取延迟或质量。PILLAR 是面向公开语料的隐私 RAG：半诚实服务器学不到查询词项和访问模式，客户端仍拿到用于增强生成的 k 篇文档。
提出 LENS，构造集合级 RAG 语料投毒以导向预设答案
Published Sep 28
Evaluated models Qwen3.6-35B-A3B , Llama-3.1-70B-Instruct , DeepSeek-V4-Pro 提出检索器后门攻击操纵智能体搜索，并用 DOU 逃避检测
Published Sep 26
Evaluated models E5 , Contriever-MSMARCO Abstract 论文展示了通过恶意检索器操纵智能体多轮搜索并利用诱饵重塑表征隐蔽后门的可行性与系统风险。
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。
提出 CIG-MIA，用上下文信息增益推断 RAG 知识库成员身份
Published Sep 14
Evaluated models Llama-3.1-8B-Instruct , Mistral-7B-Instruct-v0.3 , Llama-2-13b-chat-hf and others6 Abstract CIG-MIA 用注入前后的答案似然差推断 RAG 库成员，灰盒可分性高于所列基线。CIG-MIA 是针对 RAG 外部知识库的成员推断攻击，同时覆盖灰盒和纯文本黑盒。
提出 GraphProfiler，用个人知识图谱从帖子历史推断敏感属性并溯源
Published Sep 11 Abstract GraphProfiler 用源链接个人知识图谱做属性推断，准确率接近文本基线，并把证据定位到少量源帖。GraphProfiler 是一个可审计的 LLM 敏感属性画像器：用源链接个人知识图谱，把推断落到具体帖子。
提出 KPI，用入度定位跨层关键路径并做 SAE 转向以解决知识冲突
Published Sep 8
Evaluated models Llama-3-8B , Llama-3.1-8B , Gemma-2-9B Abstract KPI 以入度关键路径替代大批 SAE 特征转向，在冲突 RAG 上提高忠实并减轻副作用。KPI 针对知识冲突 RAG 中的 SAE 转向：相关性批量改特征会带入冗余，少量因果上关键的特征即可完成转向。
Proposes SHAQ, which replaces document embeddings with shadow query embeddings to defend against embedding inversion.
Published Sep 4
Evaluated models GTR-T5 encoder , DPR Abstract SHAQ replaces document embeddings with shadow query embeddings.SHAQ is a defense against EIA for cloud vector databases: instead of directly modifying document embeddings, it replaces them with shadow query embeddings.
提出 CodePoisonRAG，对检索增强代码生成的知识库投毒以植入漏洞
Published Sep 3
Evaluated models Qwen 3.5 9B , Code Llama 13B , DeepSeek-Coder-V2 16B Abstract CodePoisonRAG 展示了 RACG 外部知识库的新攻击面，在较低投毒率下可定向诱发指定漏洞并部分抵御防御。
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。
提出 VerTox，用可验证奖励强化学习生成误导文档并投毒检索语料
Published Sep 1
Evaluated models SimLM-base , BGE-base , Cohere-embed-english-v3.0 and others8 Abstract VerTox 以可验证奖励微调小 LLM，生成能抬高排序并腐蚀事实的投毒文档。VerTox 用可验证奖励把小 LLM 微调成语料投毒生成器，用来探测神经排序器在注入文档下的暴露面。
提出 LeakGauge，用行为后缀的 prefill 对数概率检测上下文泄露
Published Aug 18
Evaluated models Gemma-4-E4B-it , Gemma-4-31B-it , Qwen2.5-14B-Instruct and others11