Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 18 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 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 提出用扰动蒸馏本地代理并离线过滤来提取黑盒模型凭据
Published Sep 29
Evaluated models DeepSeek-Coder-7B , LLaMA-3-8B , Qwen2.5-Coder-7B and others6 Abstract 论文提出扰动蒸馏与离线过滤两阶段框架，实现了 output-only 访问下延迟降低的黑盒大模型 API key 提取。
提出用邻居分数替代参考模型的单轮成员推断
Published Sep 29
Evaluated models 目标分类模型（架构与训练流程遵循 Aerni et al.） Abstract 邻居查询在单模型上恢复逐样本校准，合成邻居加早期检查点最接近 LiRA。本文研究 one-round 成员推断 ：只有一个目标模型、不能再训练参考模型时，如何仍做逐样本校准，并用于单次运行的 DP 审计。
提出 Leaky，用新鲜轨迹的 token 对数概率差推断 OPD 训练记录成员身份
Published Sep 27
Evaluated models Qwen3-1.7B , Qwen3-4B , Qwen3.5-2B and others5 提出 RAPID，离线把抗蒸馏扰动写入文生图解码器
Published Sep 15
Evaluated models PixArt , SSD , SDXL and others4 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。
提出严格黑盒成员推断 WPMIA，用采样估计词级概率判断训练成员
Published Sep 8
Evaluated models OPT-6.7B , Pythia-6.9B , LLaMA-13B and others12 Abstract WPMIA 从续写估计词级似然并对比前缀，黑盒上多数优于所列基线。WPMIA 是面向严格黑盒的 LLM 预训练数据成员推断：攻击者只能看到文本续写。
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.
提出针对微调 TTS 的黑盒成员推断攻击
Published Sep 2
Evaluated models CosyVoice2 , F5-TTS , XTTS-v2 Abstract 黑盒 TTS 成员推断以 recitation 加分层语音表示为分数，说话人级强于记录级，DP-SGD 可压到随机附近。作者给出一个针对微调文本转语音模型的黑盒成员推断框架，分别审计说话人是否进入微调集，以及某一条文本–音频记录是否进入微调集。微调 TTS 以合成文本和参考语音双条件生成，既有生成模型 MIA 的单条件查询和图像/文本上的逐点比较不能直接套用。作者用 scorable extent 与 memorization elicitation 比较五种查询，认为只有 recitation（用目标转写和干净目标语音要求模型复现）同时满足两条，并把它作为主查询。
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 SkillClone，仅凭良性任务交互重构闭源 Agent 技能
Published Aug 5
Evaluated models DeepSeek-Flash , DeepSeek-Pro , GLM-5.1 and others5 Abstract 论文揭示了仅靠良性任务交互即可重构闭源智能体技能隐藏功能的风险，表明功能保密需要限制累积信息泄露。论文从功能保密视角系统研究了大语言模型智能体技能的行为重构威胁。
训练自博弈红队智能体 GPT-Red，规模化生成提示注入与越狱攻击
Published Jul 29
Evaluated models GPT-5.6 , GPT-5.5 , GPT-5.4 and others8 提出 SigLeak，从黑盒 Agent 执行轨迹推断专有技能
Published Jul 28
Evaluated models GPT-5.4-mini , GPT-5.5 , GLM-5.2 and others4 Abstract 提出了通过良性查询和对照轨迹推断黑盒专有技能的 SigLeak 框架，揭示了智能体执行可见性带来的行为侧信道泄露风险。
提出嵌入推断攻击 EIA，在黑盒 IR 中识别所用嵌入模型
Published Jul 1
Evaluated models e5-small , e5-small-v2 , e5-base and others19 Abstract EIA 用无序文档集的差异从候选中识别嵌入模型，并给出 reranker 与阈值下的计数。EIA 是在黑盒 IR 上识别所用嵌入模型的攻击。 。
Propose soft prompt defense AREA, re-anchoring attention to mitigate system prompt leakage
Published Jun 17
Evaluated models Llama-2-7B-chat-hf , Llama-3.1-8B-Instruct , Mistral-7B-Instruct-v0.3 and others8 Abstract The authors measure commercial prompt leakage, propose attention drift, and use AREA to strike a trade-off between usability and leakage resistance.The authors study system prompt leakage in real LLM applications and propose AREA, a mitigation method that does not modify weights.
提出 MEntA，用非模板查询推断文档是否属于 RAG 检索库
Published May 23
Evaluated models Phi4-14B , Llama3.1-8B , CommandR-7B and others5 提出 Zero2Text，无需训练地跨域反演文本嵌入
Published Feb 2
Evaluated models GTR-Base , Qwen3-Embedding-0.6B , Text-Embedding-3-small and others4 Abstract 零训练在线对齐可在未知域、无泄漏对时从黑盒 embedding 还原句子。Zero2Text 是一种不训练 decoder、也不使用泄漏文本–向量对的文本 embedding 反演，针对 RAG 向量库在严格黑盒、目标域未知时的还原。
提出 NeuroFilter，用激活探针过滤智能体多轮隐私攻击
Published Jan 21
Evaluated models GPT-OSS 20B , Qwen 2.5 32B Instruct , Llama 3.3 70B and others8 You have reached the end