MobileInject：首个针对移动智能体的多模态注入攻击安全基准
MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection
手机上的 AI 智能体会被藏在其他 App 里的恶意内容带偏，这篇论文用 108 个实例测了一圈，还给了诊断框架，做移动智能体的可以看看怎么防。
arXiv 论文提出 MobileInject，这是首个评估移动智能体多模态注入攻击的基准。该基准提供高保真交互式移动评测框架，覆盖 11 个场景、9 类安全风险和 108 个可执行风险实例。作者提出跨模态一致性注入（Cross-Modal Consistency Injection）方法，并设计了 Multi-Role Collaborative Deception 和 Reasoning-Camouflage Injection 两种增强攻击手段。实验显示移动智能体普遍易受多模态注入影响，许多失败源于推理早期阶段的推理劫持。
MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection
Multimodal large language model (MLLM)-based mobile agents are rapidly evolving from conversational assistants into autonomous systems that perceive, reason over, and act on smartphone environments. This capability also exposes a new security risk: adversaries can embed malicious objectives in cross-application mobile content and steer agent behavior through indirect multimodal injection. Although prompt injection has been studied in desktop and web settings, its cross-modal properties in mobile ecosystems remain poorly understood, and existing security analyses are still limited. To close this gap, we introduce MobileInject, the first benchmark for evaluating mobile agents against multimodal injection attacks and reasoning-to-action security risks. MobileInject provides a high-fidelity interactive mobile evaluation framework covering 11 scenarios, 9 security-risk categories, and 108 executable risk instances. It further introduces Cross-Modal Consistency Injection to exploit corroboration across modalities, two enhanced attack methods, Multi-Role Collaborative Deception and Reasoning-Camouflage Injection, to intensify trust manipulation and reasoning hijacking, and a Reasoning Security Diagnosis Framework for fine-grained failure analysis. Systematic experiments show that mobile agents are broadly vulnerable to multimodal injection, and that many failures stem from reasoning hijacking at early stages. These findings establish MobileInject as a systematic cross-modal benchmark for studying and improving the security of mobile agents. Code release details are provided in the Appendix Open Science section.
