AttacksarXiv 2610.09708
研究者提出利用祖先 VLM 的黑盒对抗补丁攻击，可降低 VLA 任务成功率
提出利用祖先 VLM 优化对抗补丁，使已部署 VLA 任务失败
- arXiv
- 2610.09708
- Published
- Layer
- Prompt layer
- Evaluated models
- OpenVLA, UniVLA, π0.5
- TechniqueGradient and representation optimization
- ComponentVision
All papers
Filter6
Attack type
Attack technique
Defense type
Impact
System type
Attack surface / entry point
Layer
System component
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 227papers have no tags yet and are not included in filtered results.
Another 227papers do not have category tags yet and are not included in filtered results.
- AttacksarXiv 2610.06814
TAPDreamer：可跨任务迁移的世界动作模型对抗补丁
TAPDreamer 用公开编码器做固定补丁。
- arXiv
- 2610.06814
- Published
- Layer
- Prompt layer
- Evaluated models
- FastWAM, DreamWAM-uncond, DreamWAM-joint and others4
- TechniqueGradient and representation optimization
- ComponentVision
- AttacksarXiv 2610.06083
研究者提出面向深度强化学习的轨迹级可迁移黑盒对抗攻击
提出轨迹级可迁移对抗攻击，降低深度强化学习策略的期望回报
- arXiv
- 2610.06083
- Published
- Layer
- Model layer
- Evaluated models
- DQN, Double DQN (DDQN)
Abstract轨迹级后退视界攻击在 CartPole 上比逐步 FGSM 类和 Sign 噪声更压低回报。
这项工作研究 DRL 上的迁移式黑盒观测攻击：受害参数不可访问时，在白盒代理上造扰动再迁移。
- DefensesarXiv 2610.05163
Researchers construct segmented prompt injection on Claude Code and Codex and release a boundary action audit benchmark
提出 PAA 方法，在边界动作前审计长流程智能体的分阶段提示注入
- arXiv
- 2610.05163
- Published
- Layer
- Application layer
- Setting
- coding agent
- Evaluated models
- Claude Code (v2.1.172, Claude Sonnet 5), Codex CLI (v0.144.0, GPT-5.5)
- DefensesMonitoring and auditing
- AttacksPrompt injection
- ComponentMonitors
Abstract论文针对长流程注入提出边界动作审计与 PAA，在保持低误阻的同时实现高拦截率。
本研究针对长流程智能体在执行任务时面临的分阶段间接提示注入威胁，提出了在动作生效前进行拦截的边界动作审计框架与路径对齐归因方法。
- DefensesarXiv 2610.03498
检测与抑制：针对 VLA 模型对抗补丁的机制可解释性防御
提出条件特征抑制防御，检出对抗补丁后抑制 VLA 内部特征
- arXiv
- 2610.03498
- Published
- Layer
- Model layer
- Evaluated models
- π0.5, SmolVLA
- DefensesInference-time intervention
- ComponentVision
Abstract条件抑制与 patch 相关的 SAE 特征，间歇攻击下可提高 SR，持续攻击下则不能。
- DefensesarXiv 2610.00450
ZoneClaw 用记忆分区防御 OpenClaw 式计算机使用 Agent 的持久记忆攻击
提出 ZoneClaw，用记忆分区防御计算机使用 Agent 的持久记忆攻击
- arXiv
- 2610.00450
- Published
- Layer
- Application layer
- Setting
- Browser and computer use
- Evaluated models
- Claude Sonnet 4.6, GPT-5.5, GLM-5.2 and others4
- DefensesInstruction–data separation
- AttacksPoisoning and backdoors
- ComponentMemory
pikit：面向间接提示注入研究与评测的可组合工具包
构建可组合工具包 pikit，评测编码智能体的间接提示注入
- arXiv
- 2609.36817
- Published
- Layer
- Application layer
- Setting
- coding agent
- AttacksPrompt injection
Abstractpikit 提供组合式间接注入评测。
pikit 是面向间接提示注入研究的组合式工具包，主要贡献是组织攻击、投递通道、防御和判定流程，而非提出新的攻击优化算法。
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
- 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。
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
- 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。
研究提出 ACE 语料库，评估内核级证据对 Agent 安全检测的有效性
构建 ACE 语料，评测内核级证据对 Agent 攻击检测的有效性
- arXiv
- 2609.28915
- Published
- Layer
- Application layer
- Setting
- coding agent
- Evaluated models
- AdaBoost, XGBoost, TabPFN and others10
- AttacksPrompt injection
- ComponentMCP and skills
AbstractACE 用配对的内核与应用层证据表明，syscall 痕迹可判别智能体攻击，两层组合通常更好。
ACE 是一份把智能体会话的内核 syscall 痕迹与应用层清单、转录配对起来的检测语料和基准。。
- AttacksarXiv 2609.13889
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
- 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。
- AttacksarXiv 2609.07051
TrojanWorld：通过想象引导对世界模型智能体植入后门
提出 TrojanWorld，用物理触发器对世界模型智能体植入想象引导后门
- arXiv
- 2609.07051
- Published
- Evaluated models
- TD-MPC2, DreamerV3, R2-Dreamer
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
AbstractTrojanWorld 揭示了世界模型智能体的供应链后门风险，通过在世界模型中操纵想象可实现对闭环动作的持续控制。
- AttacksarXiv 2608.10393
DURA：用扩散模型生成自然对抗补丁攻击 VLA 机器人模型
提出 DURA，用扩散模型生成自然对抗补丁操控 VLA 机器人动作
- arXiv
- 2608.10393
- Published
- Layer
- Prompt layer
- Evaluated models
- OpenVLA-7B, π0-FAST, openvla-7B
- TechniqueCross-modal payloads
- ComponentVision
AbstractDURA 用扩散潜空间轨迹生成自然补丁，白盒与黑盒都能把 VLA 导向指定动作。
DURA 是针对 VLA 的扩散式、补丁内容不受限的机器人攻击，同时支持白盒梯度和只看动作输出的黑盒。
- AttacksarXiv 2606.09499
研究者提出针对世界模型的机器人学习管线投毒攻击
提出 VPH 与 VTH，只改视频帧劫持世界模型并投毒下游策略
- arXiv
- 2606.09499
- Published
- Evaluated models
- Cosmos-Predict 2.5, Cosmos-Predict 2.5 AC, Dino WM and others4
- AttacksPoisoning and backdoors
- TechniqueGradient and representation optimization
- ComponentVideo
Abstract只改视频帧经世界模型投毒。
只改看似安全的视频帧，经世界模型之后才改变下游机器人策略。 问题在于世界模型进入数据生成后，数据集检查看到的仍是安全演示，合成轨迹却可以变危险。
- DefensesarXiv 2605.17380
Uber proposes ADR enterprise-level agent detection system, deployed on 7,200 hosts for ten months
提出企业级检测系统 ADR，识别编程 Agent 的提示注入与恶意 MCP
- arXiv
- 2605.17380
- Published
- Layer
- Application layer
- Setting
- coding agent
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentMCP and skills
Abstract提出了端点因果遥测、两级在线分流与离线红队闭环的 ADR 系统，并在生产环境中验证了有效性。
- DefensesarXiv 2603.14707
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
- 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.
- DefensesarXiv 2602.10915
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
- 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..
MobiRed 框架测评八款移动 LLM Agent 的第三方渠道提示注入攻击
用 MobiRed 评测移动 LLM Agent 面对第三方渠道的提示注入
- arXiv
- 2510.27140
- Published
- Layer
- Application layer
- Setting
- Browser and computer use
- Evaluated models
- Mobile-Agent-E, AppAgent, AutoGLM and others8
- AttacksPrompt injection
Abstract论文评估了移动 LLM 智能体作为 confused deputy 的易受攻击性，作者称非应用控制通道可诱导智能体执行多步越权危害。
- AttacksarXiv 2505.23266
AdvOF：用对抗物体融合攻击 VLM 驱动的视觉语言导航智能体
提出 AdvOF，生成对抗物体误导视觉语言导航智能体的场景感知
- arXiv
- 2505.23266
- Published
- Layer
- Application layer
- Attacker
- White-box
- Evaluated models
- Lseg, Clip, ViT-L/16 and others5
- AttacksDetection evasion
- TechniqueGradient and representation optimization
- ComponentVision
AbstractAdvOF 以多视角融合生成对抗物体。
AdvOF 是针对 VLM 驱动 VLN 服务导航的对抗物体攻击。
You have reached the end