作者位次 #5/7ACL 2026Poster· Natural Language Processing
XOXO : Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants
Adam Štorek · Mukur Gupta · Noopur Bhatt · Aditya Gupta · Janie Kim · Prashast Srivastava · Suman Jana
摘要
AI coding assistants automatically gather context from potentially untrusted sources to generate code recommendations. We introduce Cross-Origin Context Poisoning (XOXO), a novel attack that exploits this automatic context inclusion by subtly manipulating code without changing its semantics. Atta...