Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 23 papers Another 240 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 WebMirage，用局部对抗图像劫持视觉网页 Agent 的浏览器操作
Published Oct 7
Evaluated models LLaVA-v1.5-13B , LLaVA-v1.6-34B , MiniCPM-o-8B and others6 Abstract 论文提出了针对网络智能体的端到端视觉红队框架 WebMirage，揭示了从视觉定位到浏览器执行的安全脆弱性。WebMirage 是一个面向视觉定位网络智能体的流水线感知端到端红队攻击框架。
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 RECAST，本地改写图表与语音并做可逆数值映射以保护远程推理隐私
Published Oct 1 用 DIBench 评测移动 GUI 智能体被 UI 注入后的决策完整性
Published Sep 29
Evaluated models Qwen2.5-VL(32B) , Qwen3-VL(32B) , GUI-Owl(32B) and others7 Abstract 论文提出移动智能体决策完整性基准 DIBench，发现欺诈 UI 注入诱导目标选择并推高完成率，通用防御收益不稳定。
提出 MMSkillRisk 基准，评测多模态技能图像中的隐藏指令诱导 Agent 越权操作
Published Sep 28
Evaluated models GPT-5.6-sol , Kimi-K2.6 , Kimi-K3 and others6 Abstract 论文提出 MMSkillRisk 基准与 NCVA 攻击，揭示多模态技能中教学图像潜藏指令可引发未授权操作并与良性任务共存。
提出 IDUnlearn-Bench，评测 VLM 个体级遗忘后的身份残留
Published Sep 27
Evaluated models Qwen3-VL-2B , Qwen3-VL-4B , Qwen3-VL-8B and others6 Abstract IDUnlearn-Bench 用四族探针显示：压低直接属性访问后，身份仍常能被反向查出、绑定或重构。IDUnlearn-Bench 评测 VLM 是否忘掉一个可跨模态识别的人，而不只是答不出某条监督事实。
提出 PMPA，经外部源向 Agent 持久记忆投毒并跨会话泄露隐私
Published Sep 12
Evaluated models DeepSeek-V4-Flash , DeepSeek-V4-Pro , Qwen3-Max Abstract 论文提出了持久记忆投毒攻击 PMPA，报告了 harness 智能体在处理外部数据时易受跨会话记忆投毒与隐私泄露的风险。
用 MMPIBench 评测多模态提示注入对 Agent 框架的影响
Published Sep 9
Evaluated models Claude Opus 4.8 , GPT-5.4 , Gemini 3.1 Pro and others6 Abstract 论文提出 MMPIBench 评测多模态提示注入对智能体的影响，发现模型主导行为、尝试远超完成，音频通道缺乏防护。
提出 FreqDoor，在频域混合振幅并对生成式 VLM 做训练时视觉后门
Published Sep 7
Evaluated models BLIP-2 (opt-2.7b) , InstructBLIP (flan-t5-xl) , LLaVA (interleave-qwen) Abstract FreqDoor 用频域振幅混合给三款 VLM 植入仅视觉的训练时后门。FreqDoor 是针对生成式 VLM 的仅视觉、训练时后门：在频域混合触发源振幅、保留干净图像相位，使触发在空间上分散。
提出 Repeat-After-Me 自适应视觉提示注入，诱导 VLM 智能体执行指定任务
Published Sep 4
Evaluated models Claude-Opus-4.7 , GPT-5.5 , Gemini-3.1-Pro and others6 Abstract 论文提出了针对黑盒 VLM 的前缀诱导自适应视觉提示注入，在多款模型上诱发了工具调用与隐私泄露。
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 PaperGuard，用图文注入与梯度扰动抬高自动审稿分数并检测恶意指令
Published Jun 11
Evaluated models Claude-sonnet-4.5 , GPT-4o , GPT-4.1 and others11 Abstract PaperGuard 测到提示注入与白盒视觉抬分，并比较分块检索防御。PaperGuard 同时评测并检测多模态 AI 审稿中的评分操纵。
Conduct adversarial attacks on product images for open-source visual shopping agents and induce wrong purchases
Published Mar 17
Evaluated models LLaVA-v1.5-7B , Qwen2.5-VL-7B Abstract The authors state that LLaVA is easily induced by three attacks to buy the wrong item, while Qwen's correct purchase rate remains close to its clean condition.The authors compare the robustness of two open-source VLM shopping agents against image adversarial perturbations in a self-built e-commerce environment.
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.
提出无监督对抗微调，加固离散图像 tokenizer
Published Feb 20
Evaluated models UniTok , UniTok-MLLM , TiTok-BL128 and others7 Abstract 无监督嵌入攻击暴露离散 tokenizer 的弱点，只微调 encoder 即可提升多任务鲁棒准确率。作者研究离散图像 tokenizer 的对抗鲁棒性，给出与任务无关的嵌入攻击，以及只微调 encoder 的无监督对抗训练。
Propose SAFT, which uses semantic description ensembles to construct adversarial examples and fine-tune the image encoder
Published Feb 13
Evaluated models ViT-B/32 , CLIP-L/14 Abstract SAFT fine-tunes the CLIP image encoder with ensemble adversarial examples from refined class descriptions to improve the trade-off between zero-shot accuracy and robustness.SAFT is a method for adversarially fine-tuning the CLIP image encoder to improve the accuracy–robustness trade-off in zero-shot classification.
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. .
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 提出 BackdoorVLM 基准，评测视觉语言模型微调中的后门攻击与防御
Published Nov 24, 2025
Evaluated models LLaVA-1.5-7B , Qwen2.5-VL-7B Abstract BackdoorVLM 统一评测 VLM 后门与防御：含文本触发在低投毒率下更易激活，现有防御跨类型不稳定。BackdoorVLM 是作者提出的 VLM 后门攻击与防御评测基准，作者称它是首个此类综合基准。