ActReal：系统级移动智能体对移动自动化检测提出挑战
ActReal: System-Level Mobile Agents Challenge Mobile Automation Detection
浏览论文内容
中文总结 AI 辅助
该研究提出ActReal框架，可生成时间对齐的触摸与六轴IMU信号，规避现有移动自动化检测，事件级平均攻击成功率达77.5%，联合检测时仍达71.1%，对移动自动化检测构成挑战。
中文摘要 AI 辅助
系统级移动智能体正从固定脚本演变为自适应系统，可持续观察界面、推理并调整动作，使自动化攻击能导航动态用户界面（UI）并完成复杂任务。现有应用通过触摸轨迹、动作时序以及触摸与惯性测量单元（IMU）信号的物理耦合来检测自动化。然而，具有特权的系统级智能体执行器可同时控制触摸屏输入和应用可见的传感器传输，使其能联合生成时间对齐的触摸信号与六轴IMU信号，从而规避这些防御机制。我们提出ActReal，这是一种针对系统级移动智能体的物理动作攻击框架。ActReal通过真实轨迹适配和物理引导的IMU生成，将语义智能体动作转换为任务有效的触摸与IMU事件。ActReal在事件层面的平均攻击成功率达77.5%；即使检测器同时观测触摸与IMU信号，其攻击成功率仍保持71.1%。
英文摘要
System-level mobile agents are evolving from fixed scripts into adaptive systems that continuously observe interfaces, reason, and adjust their actions, allowing automated attacks to navigate dynamic UIs and complete complex tasks. Existing applications detect automation using touch trajectories, action timing, and the physical coupling between touch and inertial measurement unit (IMU) signals. However, a privileged system-level agent executor can control both touchscreen input and application-visible sensor delivery, enabling it to jointly generate time-aligned touch and six-axis IMU signals and evade these defenses. We present ActReal, a physical-action attack framework for system-level mobile agents. ActReal converts semantic agent actions into task-valid touch and IMU events using genuine-trajectory adaptation and physics-guided IMU generation. ActReal achieves a mean event-level attack success rate of 77.5\%; even when detectors jointly observe touch and IMU, its attack success rate remains 71.1\%.
发表机构
- North Carolina State University（北卡罗来纳州立大学）
- Indiana University（印第安纳大学）
机构由 AI 辅助整理，请以论文原文为准。
