<ul><li>GUI agents, powered by large foundation models, can interact with digital interfaces, enabling various applications in web automation, mobile navigation, and software testing.</li><li>This survey examines the trustworthiness of GUI agents in five critical dimensions: security vulnerabilities, reliability in dynamic environments, transparency and explainability, ethical considerations, and evaluation methodologies.</li><li>Major challenges include vulnerability to adversarial attacks, cascading failure modes in sequential decision-making, and a lack of realistic evaluation benchmarks.</li><li>Establishing robust safety standards and responsible development practices is essential to advance trustworthy GUI agents.</li></ul>

Towards Trustworthy GUI Agents: A Survey

Discover more