Some text is shown in its original language while the English translation is being prepared.
Oct 12 · Monday
All papers Found 214 papers Another 336 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 “Organized first” shows papers with tags or public deep readings first. Each group is ordered by original publication date, newest first, with undated papers last. “Latest publication” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and deep readings 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.
Propose KVeil, which adds perturbations to face videos to prevent unauthorized customization from reproducing identity
Published Oct 9
Evaluated models Wan2.2-TI2V-5B 、 HunyuanVideo-1.5 、 Kling 3.0 and others4 Abstract KVeil adapts LETHE's reference-reading disruption to the challenge's two stages, ranking first on the leaderboard in both Final columns.
Proposes LETHE, which perturbs reference images to block unauthorized image-to-video
Published Oct 9
Evaluated models Wan2.1-I2V-14B 、 CogVideoX-5B-I2V 、 LightX2V and others6 Abstract LETHE suppresses the diversity of reference values and attracts attention, making protected images difficult to animate faithfully.LETHE is a protective perturbation added to personal images before publication, used to counter unauthorized image-to-video generation.
Diagnose whether compliance system rulings change with perturbations to regulatory rules
Published Oct 9
Evaluated models Llama-3.3-70B-Instruct 、 Llama-3.1-8B-Instruct 、 Qwen2.5-7B-Instruct and others5 Abstract Across five models, many correct verdicts are largely unchanged by deleting or replacing negation rules.Use behavioral counterfactuals and activation probes to audit whether compliance rulings rely on the given rules. The authors aim to separate two kinds of seemingly identical correct rulings: those that use the given rules, and those obtained from case surface features or training patterns.
提出 IRIS，用意图恢复率区分遮蔽越狱下无害输出的原因
Published Oct 8
Evaluated models GPT-4o 、 Claude Sonnet 4.5 、 Claude Opus 4.5 and others6 Abstract 无害输出的证据权重取决于任务是否被恢复。IRIS 把意图恢复当作中间信号，用来解释意图遮蔽提示下为何没有出现有害协助。
测量 LLM 版本更替对科学摘要 AI 改写检测器的影响
Published Oct 8
Evaluated models RoBERTa-base 、 Pangram Abstract 作者称检测器的基准准确率只是临时的，每次发布都要连同更早版本重验。作者量化的是：科学摘要的 AI 改写筛查，在 LLM 版本不断更换、而人类摘要误标必须少见时，会怎样变。问题来自期刊和会议已经按分数阈值筛查投稿，但基准多停在评估时可得的版本上。
构建 EpiReal-Bench，评测图像生成器将虚假主张渲染为可信证据
Published Oct 8
Evaluated models GPT-Image-2 、 Nano Banana 2 、 Grok Imagen 2.0 and others4 Abstract 四款商用图像模型能把假主张画成可信证据。EpiReal-Bench 用来量商用图像生成器会不会把虚假现实主张画成可信视觉证据。
适配多种已发表说服评测并比较模型排名
Published Oct 7
Evaluated models Claude-Fable-5.1 、 GPT-5.6-Sol 、 Kimi-K2.6 and others15 Abstract 说服分数混合能力与意愿，换任务后同一模型的排名可以差很多。这项研究比较的是自动化说服评测是否一致，而不是哪一种分数更正确。
提出利用祖先 VLM 优化对抗补丁，使已部署 VLA 任务失败
Published Oct 7
Evaluated models OpenVLA 、 UniVLA 、 π0.5 比对捐赠对话史与众包提交，测量 AI 代答的集中度与获批
Published Oct 7
Published Oct 7
Evaluated models Gemma 2 9B 、 Gemma 3 4B 、 Llama 3.1 8B and others6 Abstract 五模型、七族表面形式的四态评测里，低有害遵从不等于读懂后的安全处理。ASRD 用四态标签检查五个开源模型如何处理非规范表面上的有害请求。
系统综述青年 AI 安全风险与对策的证据阶段
Published Oct 6 Abstract 作者称多数风险-对策关联停在提议，并主张把目标扩向安全的青年发展。
提出 STCA，对驾驶视频 VLM 构造可迁移的时空对抗扰动
Published Oct 6
Evaluated models Video-LLaVA-7B 、 Qwen2.5-VL-7B 、 Dolphins 提出监控深伪基准 CCDF，在统一编码后评测检测器对伪造犯罪事故录像的识别
Published Oct 6
Evaluated models C2P-CLIP 、 ForgeLens 、 D3-Im and others10 Abstract 提出消除格式捷径的监控深度伪造基准 CCDF，揭示现有检测器难以识别商用生成视频。
提出 LADE，用首 token 暗知识在生成前过滤越狱查询
Published Oct 6
Evaluated models Llama-2-7B-Chat 、 Llama-3-8B-Instruct 、 Qwen2-7B-Instruct and others13 Abstract 作者用 LADE 在生成前过滤有害查询，并称八个模型中六个的 Held-out 平均最好。LADE 是一种只读首 token 输出概率的防御，用来在生成前挡下可能引出有害回复的查询。
提出 ATLAS 用水平集估计恢复黑盒分类器的对抗输入集合
Published Oct 6
Evaluated models LeNet5 、 ResNet50 (CIFAR-10 standard) 、 ResNet50 (ImageNet standard) and others5 Abstract ATLAS 用主动水平集估计构造黑盒对抗集，作者称其集合比单点攻击更具代表性。ATLAS 是一个查询式 black-box 框架，用来构造诱发失败的对抗输入集合，供鲁棒性审计使用。
TAPDreamer 用公开编码器做固定补丁。
Published Oct 6
Evaluated models FastWAM 、 DreamWAM-uncond 、 DreamWAM-joint and others4 提出 Intent-Eval 基准，测量多轮对话里模型对已否决意图的混淆
Published Oct 5
Evaluated models Qwen3.6-27B 、 Qwen3-8B 、 Qwen3-4B-Instruct-2507 and others10 Abstract Intent-Eval 比较澄清、拒绝与修订。Intent-Eval 测的是多轮对话里，模型会不会只执行仍生效的要求。用户可以澄清、拒绝或接受变更。被提到后又失效的内容不该进入答案。
用翻译前缀做跨语言训练数据提取，恢复英语训练文本中的 PII
Published Oct 5
Evaluated models GPT-Neo 1.3B 、 GPT-Neo 2.7B 、 GPT-J 6B and others7 Abstract 跨语言 TDE 能恢复英语记忆的 PII，转移随多语训练和措辞保真变化。这篇工作检验训练数据抽取是否跨语言：英语段落里记住的 PII，能否被其他语言的前缀逐字抽出。
评测文本守卫与激活探针能否拦住机器人隐含伤害指令
Published Oct 5
Evaluated models π0.5 、 OpenVLA-OFT 、 Llama Guard 3 and others10 形式化 watchman 防御以阻止序贯马赛克攻击
Published Oct 5
Evaluated models Qwen3.6-35B-A3B 、 Gemma-4-26B-A4B-it 、 DeepSeek-V2-Lite (16B-A2.4B) Abstract watchman 理论给出零失败且有用的条件。这篇工作同时给出序贯马赛克防御的博弈理论，以及冻结 LLM 上的分角色自博弈训练。