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

Oct 12 · Monday

All papers

Found 10 papers

Filter3

Attack type

Prompt injection6

Attack technique

Cross-modal payloads3

Impact

Unauthorized actions6

System type

Models and APIs19 LLM applications4 AI Agent10 coding agent1 Embodied systems and robotics3

Attack surface / entry point

Web pages and interfaces4 Images, audio and video5

Layer

Application layer9

System component

MCP and skills15 Memory25 RAG3 Guardrails and judges22 Monitors24 Reasoning chains5 Permissions and sandboxing12 Vision10 Multimodal12

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.

System type：AI Agent System type：coding agent System component：Vision Clear all

Another 261papers do not have category tags yet and are not included in filtered results.

Evaluation and benchmarksarXiv 2610.11942Oct 8
LGWM: Verifying GUI agent screen transitions with action-conditioned world models
Proposes LGWM, using an action-conditioned world model to verify GUI agent screen transitions.
arXiv
2610.11942
Published
Oct 8
Layer
Application layer
Setting
Browser and computer use
Evaluated models
LGWM
- DefensesMonitoring and auditing
- AttacksPrompt injection
- ComponentMonitors
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.03938Oct 3
Paper finds multimodal models' refusal failure rate rises by up to 68.7% after tool use is enabled
评测 ReAct 工具调用对多模态模型拒答有害请求的削弱
arXiv
2610.03938
Published
Oct 3
Layer
Application layer
Setting
AI Agent
Evaluated models
Gemini-2.5-Pro, Gemini-3.1-Pro-Preview, Claude Opus 4.6 and others13
- RiskInappropriate refusal
- ComponentVision
Abstract论文揭示了工具调用范式削弱 MLLM 拒答能力的现象，分析了稀释与偏移机制并验证了重注缓解方案。
论文系统评估了智能体工具调用范式对多模态大语言模型拒答能力的影响，指出了工具增强视觉推理背后的安全隐患。核心探讨的问题在于：当 MLLM 从单次推理转向通过 ReAct 循环调用外部工具（打标、缩放、OCR、代码执行）时，工具使用机制本身是否会降低模型拒答有害请求的概率。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.38948Sep 30
DrivingBench 发布：让视觉语言模型驾驶丰田 Corolla 绕桩
提出 DrivingBench，评测通用视觉语言模型能否闭环驾驶真车
arXiv
2609.38948
Published
Sep 30
Layer
Application layer
Setting
Embodied systems and robotics
Evaluated models
GPT-6 Astra, Claude Fable 5.1, Grok 4.6 and others4
- ComponentVision
Abstract仅 Astra 第二次跑完低速锥桶路线。
DrivingBench 评测通用 VLM 能否自己闭环开真车，推理延迟也算进任务。
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
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 2604.12447Apr 14
HazardArena：面向 VLA 模型的语义安全评测基准
提出 HazardArena 基准，用孪生场景评测 VLA 的语义安全
arXiv
2604.12447
Published
Apr 14
Layer
Model layer
Setting
Embodied systems and robotics
Evaluated models
OpenVLA-OFT, π0, NORA and others4
- RiskDangerous agent actions
- ComponentVision
Abstractsafe-only 微调提升良性执行，也提升匹配不安全孪生上的危险完成。
HazardArena 评测 VLA 在运动要求不变时，能否因语义风险而停手。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2603.11987Mar 12
LABSHIELD：面向科学实验室安全推理与规划的多模态基准
提出 LABSHIELD，评测科学实验室智能体的安全推理与规划
arXiv
2603.11987
Published
Mar 12
Layer
Application layer
Setting
science agent, Embodied systems and robotics
Evaluated models
GPT-5.2, GPT-o3, GPT-o4-mini and others20
- RiskDangerous agent actions
- ComponentVision
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
Evaluation and benchmarksarXiv 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