AgentRAE: Remote Action Execution through Notification-based Visual Backdoors against Screenshots-based Mobile GUI Agents

TL;DR

This paper introduces AgentRAE, a backdoor attack on mobile GUI agents that uses natural notification triggers to induce remote actions, revealing new security vulnerabilities in screenshot-based mobile interfaces.

Contribution

It presents a novel two-stage backdoor attack method that effectively manipulates mobile GUI agents using benign visual triggers, achieving high success rates and evading defenses.

Findings

Over 90% attack success rate on ten mobile operations

Effective against eight state-of-the-art defenses

Triggers are hard to visually detect

Abstract

The rapid adoption of mobile graphical user interface (GUI) agents, which autonomously control applications and operating systems (OS), exposes new system-level attack surfaces. Existing backdoors against web GUI agents and general GenAI models rely on environmental injection or deceptive pop-ups to mislead the agent operation. However, these techniques do not work on screenshots-based mobile GUI agents due to the challenges of restricted trigger design spaces, OS background interference, and conflicts in multiple trigger-action mappings. We propose AgentRAE, a novel backdoor attack capable of inducing Remote Action Execution in mobile GUI agents using visually natural triggers (e.g., benign app icons in notifications). To address the underfitting caused by natural triggers and achieve accurate multi-target action redirection, we design a novel two-stage pipeline that first enhances the agent's sensitivity to subtle iconographic differences via contrastive learning, and then associates each trigger with a specific mobile GUI agent action through a backdoor post-training. Our extensive evaluation reveals that the proposed backdoor preserves clean performance with an attack success rate of over 90% across ten mobile operations. Furthermore, it is hard to visibly detect the benign-looking triggers and circumvents eight representative state-of-the-art defenses. These results expose an overlooked backdoor vector in mobile GUI agents, underscoring the need for defenses that scrutinize notification-conditioned behaviors and internal agent representations.