Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 10 papers Another 254 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.
开环审计冻结视觉语言安全分，发现其反映场景模板而非危险感知
Published Oct 7
Evaluated models CLIP ViT-B/32 , CLIP ViT-L/14 , Qwen2-VL-7B Abstract 论文审计了冻结 VLM 安全评分机制，指出其反映场景模板而非危险感知，为安全强化学习评估提供了严谨基准。本文是一项针对安全强化学习中冻结视觉语言模型（VLM）安全评分机制的实证审计研究。
分析潜空间图像水印对像素扰动的内在鲁棒性上限
Published Oct 6
Evaluated models Stable Diffusion v2-1 Abstract 作者称当前潜空间水印在低 FPR 下受扩张映射与分布偏移的限制。
固定有害指令，单轴归因图像到文本越狱的图像属性
Published Oct 4
Evaluated models GPT-4o , Claude Sonnet 4.5 , Qwen3-VL-8B-Instruct and others6 Abstract 固定文本的图像越狱拆解，只在 Qwen 上给出一条有界相关性归因。
遮挡审计 AdvWave-P 音频越狱的频带必要性与解码层关联
Published Oct 4
Evaluated models Qwen2-Audio-7B-Instruct , LLaMA-Omni Abstract AdvWave-P 的八频带排序与能量相关。这是对加性音频越狱 AdvWave-P 的频率与解码器深度审计，受害模型主要是 Qwen2-Audio-7B-Instruct，不提出新攻击。
分析隐蔽推理在思维链监控下的信息足迹下界与不可读性
Published Sep 29
Evaluated models Qwen2.5-7B-Instruct , Llama-3.1-8B-Instruct , Qwen 3.5 397B-A17B and others12 Abstract 论文从理论与实证探明了思维链监控的边界：复杂隐蔽计算必然泄露信息足迹且需承担长度税，但该足迹可被在线加密而不可读。
分析零训练 LLM+OVOD 流水线中 CAAP 与 SNAP 分离的来源
Published Sep 26
Evaluated models Gemma-3 4B , YOLO-World X , Qwen2.5-VL 7B and others4 用五阶段蒙特卡洛分析奖励作弊如何导致 Agent 围堵失效
Published Sep 26 Abstract 分层控制的模拟事件率低于弱控制以及单独隔离或单独监控。这项研究用蒙特卡洛把奖励黑客接到外部安全事件上，比较的是控制组合，不是 Hugging Face 事件的再现概率。
刻画单迹监控对跨执行超性质的监督缺口
Published Sep 7
Evaluated models Llama-3.1-8B , Mistral-24B , GPT-4o-mini and others9 Abstract 单迹监督的上界由 TV 决定。论文测量单迹安全监控相对 2-safety 超性质 能看见多少：跨租户泄漏、觉察到被评估、策略性表现不佳都由两次执行之差定义，一条轨迹装不下判定。
分析外部记忆对智能体处理不可回答问题的影响
Published Aug 28
Evaluated models DeepSeek-V3.2 , Qwen3-235B-A22B-Instruct-2507 , GPT-5.5 Abstract 记忆能选择性提高 UAQ 的可接受回应，但跨数据集不稳定，且更依赖可迁移的行为指导。这份研究在同一智能体框架里检查外部记忆会不会让不可回答问题的处理更稳，以及稳来自哪一种存储内容。
因果审计视觉工具调用，分离观察贡献与动作诱发捷径
Published Aug 7
Evaluated models DeepEyes , Pixel Reasoner , Mini-o3 and others6 Abstract 聚合增益集中在 Calibrated 少数轨迹，作者称之为视觉工具使用的错觉。对六个 thinking-with-images 模型做因果审计，检查 crop-and-zoom 返回的观察是否中介最终答案。
You have reached the end