Translation in progress Some entries still include text in the original language.
Oct 13 · Tuesday
All papers Found 15 papers Another 201 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 Safety-Aware Pruning，缓解视觉 token 剪枝放大的多模态越狱
Published Oct 7
Evaluated models LLaVA-1.5-7B Abstract 剪枝去掉背景 token 后注意力塌向恶意前景。这篇工作评估视觉 token 剪枝如何改变 VLM 在多模态越狱下的行为，并给出推理时防御 SAP。
提出 TRACER，从权重差识别扩散模型被擦除概念
Published Oct 5
Evaluated models Stable Diffusion v1.5 , Stable Diffusion 3 , FLUX.1 and others5 Abstract TRACER 用权重足迹识别未披露擦除概念并估计个数，作者称数秒内完成且准确率高于对照。TRACER 针对的是遗忘扩散模型上的目标识别：提供者从公开基座 W 用已发表方法擦掉未知集合 S⋆，只发布 W′。攻击者还有假定包含这些概念的词表，但不知擦了谁、擦了几个、用了什么算法。
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 AEGIS，用中层内部信号选择性激活后层适配器拦截音频越狱
Published Sep 24
Evaluated models Qwen2-Audio-7B , VITA-1.5 , Ultravox v0.5 and others6 提出 PALS，用潜空间平滑防御全双工语音对话的对抗扰动
Published Sep 23
Evaluated models Moshi-style agent 提出 VidMark 水印方案，核验视频生成模型的输出来源与所有权
Published Sep 20
Evaluated models Stable Video Diffusion (SVD) , Open-Sora , Wan Abstract VidMark 加解码器引导微调，把模型签名写入 VGM 输出并用于两项核验。Huang 等人提出一套面向视频生成模型的生成内嵌水印方案，用来同时判断一条视频是否来自受保护模型，以及一个嫌疑模型是否为该模型的拷贝。
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 SPARK，在预填充阶段修复多模态 KV 记忆以防御视觉语言模型越狱
Published Sep 13
Evaluated models LLaVA-OneVision-7B , Chameleon-7B , Qwen2-VL-7B and others4 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 SWhisper，用近超声波向语音驱动 LLM 隐蔽注入越狱提示
Published Mar 14
Evaluated models Meta-Llama-3.1-8B-Instruct , Gemma-3-4B , Qwen2.5-7B-Instruct and others9 Proposes SafeThink, an inference-time defense that monitors the chain of thought and injects a redirect prefix when it falls below a threshold.
Published Feb 12
Evaluated models R1-Onevision-7B , OpenVLThinker-7B , VLAA-Thinker-7B and others6 Proposes the Aegis red-teaming framework for multi-turn attacks on high-risk voice agents.
Published Feb 7
Evaluated models GPT-4o , GPT-4o-mini , Gemini-1.5 Pro and others7 Abstract Aegis red-teams three types of voice agents: query-based access eliminates authentication and leakage successes, but behavioral attacks remain.Aegis uses multi-turn red-teaming evaluation on ALLM voice agents already integrated into business systems. The authors call this the first systematic red-teaming framework in this setting.
Attacks arXiv 2512.20168 · Dec 23, 2025 提出双重隐写越狱 Odysseus，用图像隐写绕过多模态系统安全过滤器
Published Dec 23, 2025
Evaluated models GPT-4o-2024-08-06 , Gemini-2.0-pro , Gemini-2.0-flash and others4 Attacks arXiv 2508.06837 · Aug 9, 2025 提出 Prometheus，从展示图反推文生图模型的在售提示词
Published Aug 9, 2025
Evaluated models Midjourney , Leonardo.ai , DALL·E and others4 Abstract 训练无关的 proxy 搜索攻击。Prometheus 是针对文生图市场 showcase 的训练无关提示词窃取：攻击者看不到在售文本，只用本地开源 proxy 恢复 subject 和 modifier，并希望换 subject 后风格仍在。
You have reached the end