Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 14 papers Another 265 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.
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。
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。
评测文生图模型的有害内容生成能力与审核检测缺口
Published Oct 5
Evaluated models SDXL , Stable Diffusion 3.5 Large , FLUX.1-dev and others12 构建多语言音视频 DeepFake 基准 BabelFake 并评测检测器
Published Oct 5
Evaluated models SpeechForensics , AVH-Align , (B)RAVEn Abstract BabelFake 为五语同意采集基准。BabelFake 是经同意与 IRB 批准采集的多语音视频 DeepFake 检测基准，用来把视觉操纵和语音合成拆开比较。
提出 CorrectGuard，在不可查看输入上估计黑盒护栏决策对错
Published Oct 2
Evaluated models Granite Guardian 3.1 2B , Qwen3Guard 8B , GPT-OSS-Safeguard-20B and others7 Abstract CorrectGuard 用外部模型估计黑盒护栏决策对错，排序和弃权可用，校准在偏移下变差。CorrectGuard 面向不能人工检查生产输入、也没有生产标签的黑盒安全护栏，用外部模型估计单条决策是否正确，并据此排序和弃权。离线基准会随数据和攻击变化，未必代表生产分布。隐私约束还可能禁止模型查看原文或可反演的稠密嵌入。
评测多轮对话中 GradSafe 越狱检测的可分性与脆弱性
Published Sep 29
Evaluated models Llama 3.1 8B Instruct , Qwen2.5-7B-Instruct Abstract CWS 显示不安全梯度在真实多轮流量中变弱，且随攻击族和模型而变。作者评估梯度越狱检测从单条提示词迁到多轮对话后还剩多少可分性，方法是用 Context Window Scanner 把 GradSafe 原封不动地套到用户轮窗口上。
构建 TriggerBench 并训练 ThinkingGuard，检测图文隐式风险
Published Sep 29
Evaluated models ThinkingGuard（Qwen3-VL-8B-Instruct） Abstract TriggerBench 隔离触发条件，ThinkingGuard 用分步归因在隐式风险检测上取得作者报告的较高平均分。这篇工作研究多模态隐式风险检测 ：图文各自良性，风险只在关键元素与触发元素交互时出现。
提出 RLCDAlignBench，零样本检测多种对齐失败
Published Sep 24
Evaluated models Jev (jev-1.13.0) Abstract 一次通用问题已能给多数对齐失败排序，大的误差来自状态和标签。RLCDAlignBench 测量用强化学习做校准决策的 Jev，能否当作对齐失败的零样本检测器。
组织 ArGuard 共享任务评测阿拉伯语表情包与提示词有害检测
Published Sep 24
Evaluated models Qwen3-VL , Qwen3-VL-8B-Instruct , MARBERTv2 and others9 评估安全监视器并提出双侧梯级微调以减少会答有害请求的漏检
Published Sep 5
Evaluated models Gemma-4-31B-IT , Qwen3-32B , Llama Guard 3 8B and others6 Abstract 论文发现安全监视器大多拦截模型已拒答请求，指出明确度偏差是共性原因，并通过双侧梯级微调提升回答请求的召回表现。
评测安全 LLM-judge 对新上下文与新政策的改判能力
Published Jun 6
Evaluated models GPT-5-2 , GPT-5-mini-08-2025 , Claude-4-5-Sonnet and others13 Abstract 作者形式化两种 judge 属性，称新 context 只在先验弱时有用，新政策则很难改判。作者度量的不是 judge 与某一套人工标签有多一致，而是它会不会吸收新 context、会不会改用另一套安全政策。
构建 MultiTurnPSB，评测四轮医疗越狱与分类器输入防御
Published May 30
Evaluated models GPT-4.1-mini , Claude Sonnet 4.5 Abstract 多轮攻击加剧医疗模型风险，分类器干预有效但受高误报率制约。MultiTurnPSB 针对患者端医疗大模型在持续交互中的安全风险，构建了包含三种攻击模态的四轮对抗评测基准。
提出 Artifact-Bench，评测 MLLM 检测并诊断 AI 生成视频伪影
Published May 19
Evaluated models Gemini 3.1 Pro , Gemini 3 Flash , Qwen3-VL 8B-Instruct and others19 Abstract Artifact-Bench 以三项任务评 MLLM 的 AIGC 伪影感知。Artifact-Bench 用来看 MLLM 能否发现 AI 生成视频中的伪影，并说明视频为何不真实。
提出 FoodGuardBench 与护栏 FoodGuard-4B，评测并降低食品危害越狱
Published Apr 2
Evaluated models Claude-3.7-Sonnet , GPT-4o , GPT-4.1 and others10 You have reached the end