AI RESEARCH
Adversarial Hubness Detector: Detecting Hubness Poisoning in Retrieval-Augmented Generation Systems
arXiv CS.AI
•
ArXi:2602.22427v2 Announce Type: replace-cross Retrieval-Augmented Generation (RAG) systems are essential to contemporary AI applications, allowing large language models to obtain external knowledge via vector similarity search. Nevertheless, these systems encounter a significant security flaw: hubness - items that frequently appear in the top-$k$ retrieval results for a disproportionately high number of varied queries.