Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 12 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.
提出 ALIBI，向恶意二进制注入不执行掩护叙事使分析器误判为良性
Published Sep 17
Evaluated models Gemini 2.5 Pro , GPT-5.5 Pro , Claude Opus 4.7 Abstract ALIBI 用二进制内的掩护叙事重释可疑静态证据，Gemini 上翻转多，另两模型主要为降级。ALIBI 是针对 LLM 恶意软件分诊的语义掩护叙事攻击：不覆盖系统指令，而把仍可见的可疑静态证据重释成良性安全产品的预期行为。
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。
提出对抗重构，仅改表述以拉高 AI 审稿分数
Published Jun 11
Evaluated models Claude Sonnet 4 , Claude Sonnet 4.5 , GPT-5-mini Abstract 揭示 AI 审稿系统易受纯表述重构操纵，建议在部署前解耦科学与写作评价。
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。
提出日志基底提示注入，操纵 SOC 分析员的分类、摘要与处置建议
Published May 23
Evaluated models gpt-4o-mini Abstract 在 gpt-4o-mini 上，人格劫持与上下文操纵可改写 SOC 分析输出，直接覆盖在分类上无效。
用简历中的不可见指令做间接提示注入，操纵招聘推荐
Published Feb 20
Evaluated models Qwen 3 30B A3B Instruct 2507 , Qwen 3 30B A3B Thinking 2507 Abstract 作者称推理在简单注入下会帮攻击圆谎，在不合逻辑的复杂注入下又会把欺骗漏出来。
提出 ER-MIA 黑盒记忆注入，用嵌入相近记忆抢占检索并改错后续回答
Published Feb 17
Evaluated models Llama3.2:3b , Gemma 3:27b , GPT-oss:20b 提出查询无关黑盒攻击 DQ-A，用可迁移文末后缀降低文档检索排名
Published Jan 31
Evaluated models Qwen-1.5-7B-Instruct , SFR-Embedding-Mistral , E5-Mistral-7B-Instruct and others10 Abstract DQ-A 以无查询黑盒后缀压低 LLM 检索排名，并在 BRIGHT 上比较三种基线。DQ-A 是一种 query-agnostic、complete black-box 的文档隐藏攻击，对象是用最后隐层相似度匹配的 LLM 检索。
提出 AST-ASIP ，把对抗指令植入编译器忽略区域以劫持代码评分
Published Jan 29
Evaluated models DeepSeek-V3.2 , Qwen3-235B , GPT-OSS-120B and others9 Abstract 作者称 RLHF 的服从性使评分脱离代码。这篇工作把自动代码评分中的失败称为 Compliance Paradox：评分模型可以离开提交逻辑，转而执行嵌在可编译代码里的隐藏指令。
提出保义释义攻击 PAA，抬高 LLM 审稿评分
Published Jan 11
Evaluated models GPT-4o , Gemini 2.5 , Sonnet 4 Abstract PAA 用保义释义抬高 LLM 审稿分。PAA 是对 LLM-as-a-Reviewer 的 black-box 攻击：只改写摘要，用评审分做 ICL 搜索，并用 BERTScore 与困惑度限制语义和自然度。
Attacks arXiv 2512.10449 · Dec 11, 2025 提出 DSAAP，以不可见文本对科学审稿 PDF 做间接提示注入
Published Dec 11, 2025
Evaluated models gpt-oss-20B , tulu3-8B , Llama 3.1-8B and others13 Attacks arXiv 2508.19287 · Aug 25, 2025 提出 prompt-in-content 攻击，用上传文档指令劫持摘要
Published Aug 25, 2025
Evaluated models ChatGPT 4o , Claude Sonnet4 , Gemini 2.5 Flash and others7 Abstract 文档内单条指令可劫持网页端摘要任务，七个平台的拦截并不一致。prompt-in-content 攻击 把指令放进会被上传的文件，使用户的普通文档任务变成触发器。
You have reached the end