作者位次 #2/5ACL 2026Poster· Natural Language Processing
Don’t Click That: Teaching Web Agents to Resist Deceptive Interfaces
Yilin Zhang · Yingkai Hua · Chunyu Wei · Xin Wang · Yueguo Chen
摘要
Vision-language model (VLM) based web agents demonstrate impressive autonomous GUI interaction but remain vulnerable to deceptive interface elements. Existing approaches either detect deception without task integration or document attacks without proposing defenses. We formalize deception-aware w...