AIBearisharXiv – CS AI · 5h ago7/10
🧠
Mobile GUI Agents under Real-world Threats: Are We There Yet?
Researchers have identified critical vulnerabilities in mobile GUI agents powered by large language models, revealing that third-party content in real-world apps causes these agents to fail significantly more often than benchmark tests suggest. Testing on 122 dynamic tasks and over 3,000 static scenarios shows misleading rates of 36-42%, raising serious concerns about deploying these agents in commercial settings.