Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 14 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 Secure-CUA，用动作事务约束计算机使用智能体的不可信影响
Published Oct 7
Evaluated models Claude Opus 5 , Gemini 3.8 Flash , GPT-5.6-Sol Abstract Secure-CUA 用每步事务约束不可信影响，良性 TSR 接近 Vanilla-CUA。Secure-CUA 要限制图形界面里不可信内容对 CUA 决策和 GUI 执行的影响，同时保留合法任务所需的不可信信息。
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 Pictionary，将不可信文本渲染成图像以防御提示注入
Published Sep 29
Evaluated models Claude Opus 4.7 , Claude Haiku 4.5 , GPT-5.5 and others12 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 用后验重加权解释多模态上下文越狱，并提出风险门控的良性示例注入防御
Published Sep 8
Evaluated models Qwen3-VL-2B , Qwen3-VL-4B , Qwen3-VL-8B and others8 Abstract 后验重加权解释上下文越狱的缩放，并支持风险门控的良性示例防御。Zhang 等把多模态 ICL 越狱写成对齐模型在安全与有害隐模式之间的推理时后验漂移，并据此做风险门控防御。
提出持续学习下的净化与选择性恢复框架，抵御逐任务训练投毒后门
Published Sep 6
Evaluated models ViT-B/16 Abstract 作者报告任务内净化与恢复可配合动态专家防御后门，但保证依赖分离条件。这是一项面向持续图像分类的后门防御研究 ：模型只使用当前任务数据，同时需要保留过去知识并避免学习恶意监督。
提出 Mind2Web-Injection 评测网页 Agent 视觉注入护栏
Published Sep 2
Evaluated models GPT-5.6-luna , Qwen3-VL-32B , Qwen3-VL-8B and others6 Abstract 作者称检测、定位和反事实响应在六个 VLM 上可分开。Mind2Web-Injection 用来检查网页截图护栏的判决是否对齐到该用的画面证据。 。
提出 SPARED，用对抗编辑数据训练基于推理的 AI 生成图像检测器
Published Aug 13
Evaluated models Qwen3.5-9B Abstract SPARED 用防捷径的编辑对抗环训练 9B 推理检测器。SPARED 是一套用于可解释 AI 生成图像检测的攻防强化学习流程，报告模型是 Qwen3.5-9B 上的第三轮防御器。
提出机器遗忘式生成图像检测，用遗忘前后特征相似度区分自然图与生成图
Published Aug 1
Evaluated models DINOv2 ViT-S/14 , DINOv2 ViT-B/14 , DINOv2 ViT-L/14 and others9 Abstract 作者用剪枝或 LoRA 遗忘拉开生成图与自然图的特征相似度，并在多个检测基准上报告结果。这篇工作把 AI 生成图像检测写成对预训练视觉模型的机器遗忘：原模型对两类图像损失都低，剪枝后生成图特征变得更不像原模型。
提出 GeoDetect 以几何分数检测视觉语言预训练模型的对抗样本
Published Jul 16
Evaluated models CLIPViT (ViT-B/16) , CLIPCNN (ResNet-50) , ALBEF and others4 Abstract GeoDetect 用几何分数检测 VLP 对抗样本。GeoDetect 是面向视觉-语言预训练模型的对抗样本检测方法，用嵌入几何而不是任务 logits 区分干净样本与对抗样本。
Proposes out-of-process dual-channel comparison classification to intercept erroneous clicks by computer-use agents
Published Mar 16
Evaluated models multi-modal-embed-small Abstract Perception errors can be exploited by swapping screen pixels.The authors frame CUA's perception failure as a security vulnerability, visual confused deputy : the agent authorizes click(x,y) based on a misread screen, and the actual landing point differs from the element it believes it is clicking.
提出 Aura，用可信内核中介移动 Agent 的身份、感知与动作控制
Published Feb 11
Evaluated models Gemini-3-Flash Abstract Aura mediates structured interactions via the Agent Kernel.Aura uses kernel-mediated structured agent interaction, replacing screen-interface mobile assistants. .
提出多轮多模态越狱，并用 FragGuard 拦截有害响应
Published Jan 9
Evaluated models LLaVa-1.6 (7B) , LLaVa-1.6 (13B) , Qwen-2-7B and others5 提出 WAInjectBench 评测网页 Agent 的提示注入检测
Published Oct 2, 2025
Evaluated models GPT-4o , Mistral-7B-Instruct-v0.1 , Llama-Prompt-Guard-2-86M and others8 Abstract WAInjectBench 比较网页智能体的提示注入检测：显式线索可被部分检出，隐蔽攻击大多漏检。WAInjectBench 是网页智能体提示注入检测的基准。作者要看现有检测器能否发现这类攻击：攻击者改网页，使智能体执行目标动作，而不是用户任务。作者称这是首个此类综合基准。
You have reached the end