Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 265 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 RECAST,本地改写图表与语音并做可逆数值映射以保护远程推理隐私
Published Oct 1 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。
提出意图驱动本地框架 Veilmind,净化发往远程模型的提示词
Published Sep 10
Evaluated models Veilmind-4B Abstract 本地模型按意图净化提示词,在 Uprise 上给出两个隐私-效用工作点。本地侧的意图驱动净化,用来降低用户提示词发往不受信任远程模型时的敏感属性暴露。
提出 SHAQ,用影子查询嵌入替换文档嵌入以抵御嵌入反演
Published Sep 4
Evaluated models GTR-T5 encoder , DPR Abstract SHAQ 用影子查询嵌入替换文档嵌入。SHAQ 是面向云端向量库 EIA 的防御:不直接改文档嵌入,而用影子查询嵌入替换它们。
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 提出软提示防御 AREA,重锚定注意力以缓解系统提示泄露
Published Jun 17
Evaluated models Llama-2-7B-chat-hf , Llama-3.1-8B-Instruct , Mistral-7B-Instruct-v0.3 and others8 Abstract 作者测量商用提示词泄漏,提出 attention drift,并用 AREA 在可用性与抗泄漏间取折中。作者研究真实 LLM 应用中的 system prompt 泄漏 ,并给出不改权重的缓解方法 AREA。
提出零知识审计协议,核验多租户 RAG 的合谋差分隐私
Published May 19 Abstract 揭示多租户 RAG 合谋泄露按根号 k 放大,提出带零知识证明的无泄露审计协议。论文针对多租户 RAG 服务在多账户协同攻击下隐私边界失效的问题展开研究。
You have reached the end