AINeutralarXiv – CS AI · 8h ago6/10
🧠
Don't Click That: Teaching Web Agents to Resist Deceptive Interfaces
Researchers introduce DUDE, a framework that teaches AI web agents to resist deceptive interface elements through hybrid-reward learning and experience summarization. The accompanying RUC benchmark demonstrates the framework reduces susceptibility to deception by 53.8% while preserving task performance, addressing a critical vulnerability in autonomous GUI interaction systems.