Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 17 papers

Filter5

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.

Attack type：Prompt injection System type：Models and APIs System type：AI Agent System type：coding agent Attack surface / entry point：Images, audio and video Clear all

Another 240papers do not have category tags yet and are not included in filtered results.

AttacksarXiv 2610.09240Oct 7
WebMirage hijacks visual web agents' browser operations with adversarial images
提出 WebMirage，用局部对抗图像劫持视觉网页 Agent 的浏览器操作
arXiv
2610.09240
Published
Oct 7
Layer
Application layer
Setting
web agent
Evaluated models
LLaVA-v1.5-13B, LLaVA-v1.6-34B, MiniCPM-o-8B and others6
- AttacksPrompt injection
- TechniqueGradient and representation optimization
- ComponentVision
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。
Paper analysisRead analysis
AttacksarXiv 2610.09027Oct 7
P-VMI：对抗图像经 KV cache 持续影响多轮对话
提出持久视觉记忆注入，使对抗图像经缓存在触发时操控输出
arXiv
2610.09027
Published
Oct 7
Layer
Infrastructure layer
Setting
Models and APIs
Evaluated models
Qwen3-8B, Qwen3-VL-8B-Instruct, Gemma-4-12B
- AttacksPrompt injection
- TechniqueDormant triggers
- ComponentVision
Abstract论文提出 P-VMI，证实对抗输入被掩蔽后仍可经 KV 缓存持久控制模型，强调了保留状态的安全风险。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.06898Sep 29
DIBench：面向移动 GUI 智能体多候选选择决策完整性的安全基准
用 DIBench 评测移动 GUI 智能体被 UI 注入后的决策完整性
arXiv
2610.06898
Published
Sep 29
Layer
Application layer
Setting
Browser and computer use
Evaluated models
Qwen2.5-VL(32B), Qwen3-VL(32B), GUI-Owl(32B) and others7
- AttacksPrompt injection
- ComponentVision
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。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.35912Sep 28
MMSkillRisk：多模态技能图像中的隐藏指令可诱导 Agent 执行未授权操作
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
arXiv
2609.35912
Published
Sep 28
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.6-sol, Kimi-K2.6, Kimi-K3 and others6
- AttacksPrompt injection
- TechniqueCross-modal payloads
- ComponentMCP and skills
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。
Paper analysisRead analysis
AttacksarXiv 2609.13889Sep 12
PMPA：针对 OpenClaw 与 Claude Code 的持久记忆投毒攻击
提出 PMPA，经外部源向 Agent 持久记忆投毒并跨会话泄露隐私
arXiv
2609.13889
Published
Sep 12
Layer
Application layer
Setting
coding agent
Evaluated models
DeepSeek-V4-Flash, DeepSeek-V4-Pro, Qwen3-Max
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
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。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.09404Sep 9
MMPIBench：多模态提示注入对六种 Agent 框架的跨框架评测
用 MMPIBench 评测多模态提示注入对 Agent 框架的影响
arXiv
2609.09404
Published
Sep 9
Layer
Application layer
Setting
AI Agent
Evaluated models
Claude Opus 4.8, GPT-5.4, Gemini 3.1 Pro and others6
- AttacksPrompt injection
- TechniqueCross-modal payloads
- ComponentVision
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。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.04859Sep 4
MM-IFEval-Pro：面向视觉语言模型的多语言抗攻击指令遵循基准
提出抗攻击多语言视觉指令遵循基准 MM-IFEval-Pro
arXiv
2609.04859
Published
Sep 4
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
Qwen3-VL-8B-Instruct, InternVL3.5-8B, MiniCPM-V4.5 and others5
- AttacksPrompt injection
- ComponentVision
AbstractMM-IFEval-Pro 以规则验证评测中英指令遵循与视觉劫持，GRPO 提高两基座平均分。
MM-IFEval-Pro 是面向 VLM 的中英多模态指令遵循基准，并配有可用规则计算奖励的 GRPO 训练集。
Paper analysisRead analysis
AttacksarXiv 2609.04533Sep 4
Repeat-After-Me：针对黑盒 VLM 的自适应视觉提示注入攻击
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
arXiv
2609.04533
Published
Sep 4
Layer
Application layer
Setting
AI Agent
Evaluated models
Claude-Opus-4.7, GPT-5.5, Gemini-3.1-Pro and others6
- AttacksPrompt injection
- TechniqueAutomated search
- ComponentVision
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。
Paper analysisRead analysis
AttacksarXiv 2605.16090May 15
研究者提出 CrossMPI：仅用图像扰动实现跨模态提示注入
提出 CrossMPI，仅用图像扰动实现跨模态提示注入
arXiv
2605.16090
Published
May 15
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
MiniGPT4-llama2, MiniGPT4-vicuna, InstructBLIP and others6
- AttacksPrompt injection
- TechniqueCross-modal payloads
- ComponentVision
Paper analysisRead analysis
AttacksarXiv 2604.14604Apr 16
The AudioHijack framework achieves covert audio prompt injection against 13 speech large models
提出 AudioHijack，用不可感知对抗音频对语音模型做上下文无关提示注入
arXiv
2604.14604
Published
Apr 16
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
SpeechGPT, GLM-4-Voice, VITA-Audio and others15
- AttacksPrompt injection
- TechniqueGradient and representation optimization
- ComponentAudio
Abstract提出了 AudioHijack 框架，揭示了 LALM 对听觉提示注入的脆弱性与传统防御的局限。
Paper analysisRead analysis
AttacksarXiv 2603.29418Mar 31
研究者提出针对商用多模态大模型的隐蔽视觉提示注入方法
提出 CoTTA 隐蔽视觉提示注入，使多模态模型输出指定指令
arXiv
2603.29418
Published
Mar 31
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
GPT-4o, GPT-5, Claude-4.5 and others4
- AttacksPrompt injection
- TechniqueCross-modal payloads
- ComponentVision
AbstractCoTTA 以隐蔽触发和双目标对齐诱导指定句子。
Paper analysisRead analysis
AttacksarXiv 2603.16960Mar 17
Adversarial attacks against modern vision-language models
Conduct adversarial attacks on product images for open-source visual shopping agents and induce wrong purchases
arXiv
2603.16960
Published
Mar 17
Layer
Application layer
Setting
web agent
Evaluated models
LLaVA-v1.5-7B, Qwen2.5-VL-7B
- AttacksPrompt injection
- TechniqueGradient and representation optimization
- ComponentVision
AbstractThe 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.
Paper analysisRead analysis
DefensesarXiv 2603.14707Mar 16
Visual Confusion Agents: Exploiting and Defending Against Perception Failures in Computer-Use Agents
Proposes out-of-process dual-channel comparison classification to intercept erroneous clicks by computer-use agents
arXiv
2603.14707
Published
Mar 16
Layer
Application layer
Setting
Browser and computer use
Evaluated models
multi-modal-embed-small
- DefensesDetection and filtering
- AttacksPrompt injection
- RiskDangerous agent actions
- ComponentGuardrails and judges
AbstractPerception 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.
Paper analysisRead analysis
AttacksarXiv 2602.15927Feb 18
研究者提出面向多轮对话的视觉记忆注入攻击 VMI
提出 VMI，用扰动图像在多轮对话中潜伏并仅在触发话题输出预定消息
arXiv
2602.15927
Published
Feb 18
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
Qwen2.5-VL-7B-Instruct, Qwen3-VL-8B-Instruct, LLaVA-OneVision-1.5-8B-Instruct and others5
- AttacksPrompt injection
- TechniqueCross-modal payloads
- ComponentVision
AbstractVMI 让扰动图像在多轮 LVLM 中潜伏，作者称触发话题出现后仍可输出预定消息。
VMI 是面向多轮 LVLM 的定向图像攻击：第三方发布带小扰动的图像，良性用户把它当作普通输入。
Paper analysisRead analysis
DefensesarXiv 2602.10915Feb 11
Blind Gods and Broken Screens: Building a Secure, Intent-Centric Mobile Agent Operating System
提出 Aura，用可信内核中介移动 Agent 的身份、感知与动作控制
arXiv
2602.10915
Published
Feb 11
Layer
Application layer
Setting
Browser and computer use
Evaluated models
Gemini-3-Flash
- DefensesInstruction–data separation
- AttacksPrompt injection
- ComponentPermissions and sandboxing
AbstractAura mediates structured interactions via the Agent Kernel.
Aura uses kernel-mediated structured agent interaction, replacing screen-interface mobile assistants..
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2510.01354Oct 2, 2025
WAInjectBench 系统评测网页 Agent 的提示注入检测方法
提出 WAInjectBench 评测网页 Agent 的提示注入检测
arXiv
2510.01354
Published
Oct 2, 2025
Layer
Application layer
Setting
web agent
Evaluated models
GPT-4o, Mistral-7B-Instruct-v0.1, Llama-Prompt-Guard-2-86M and others8
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
AbstractWAInjectBench 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。
Paper analysisRead analysis
AttacksarXiv 2406.12814Jun 19, 2024
论文提出 ARE 框架，在 VisualWebArena 上评估多模态 Agent 的对抗鲁棒性
提出 ARE 框架与图像文本攻击，评测多模态网页 Agent 的对抗鲁棒性
arXiv
2406.12814
Published
Jun 19, 2024
Layer
Application layer
Setting
web agent
Evaluated models
GPT-4o, GPT-4V, Claude-3-Opus and others4
- AttacksPrompt injection
- TechniqueGradient and representation optimization
- ComponentVision
Abstract系统评估多模态网页智能体的脆弱性，指出推理时计算组件被攻破会加剧系统风险。
Paper analysisRead analysis

You have reached the end

AI Safety Daily

Read the latest issueOne issue per day, updated as events develop

All papers

Attack type

Attack technique

Impact

System type

Attack surface / entry point

Layer

System component

WebMirage hijacks visual web agents' browser operations with adversarial images

P-VMI：对抗图像经 KV cache 持续影响多轮对话

DIBench：面向移动 GUI 智能体多候选选择决策完整性的安全基准

MMSkillRisk：多模态技能图像中的隐藏指令可诱导 Agent 执行未授权操作

PMPA：针对 OpenClaw 与 Claude Code 的持久记忆投毒攻击

MMPIBench：多模态提示注入对六种 Agent 框架的跨框架评测

MM-IFEval-Pro：面向视觉语言模型的多语言抗攻击指令遵循基准

Repeat-After-Me：针对黑盒 VLM 的自适应视觉提示注入攻击

研究者提出 CrossMPI：仅用图像扰动实现跨模态提示注入

The AudioHijack framework achieves covert audio prompt injection against 13 speech large models

研究者提出针对商用多模态大模型的隐蔽视觉提示注入方法

Adversarial attacks against modern vision-language models

Visual Confusion Agents: Exploiting and Defending Against Perception Failures in Computer-Use Agents

研究者提出面向多轮对话的视觉记忆注入攻击 VMI

Blind Gods and Broken Screens: Building a Secure, Intent-Centric Mobile Agent Operating System

WAInjectBench 系统评测网页 Agent 的提示注入检测方法

论文提出 ARE 框架，在 VisualWebArena 上评估多模态 Agent 的对抗鲁棒性