AI RESEARCH
Led to Mislead: Adversarial Content Injection for Attacks on Neural Ranking Models
arXiv CS.CL
•
ArXi:2605.01591v1 Announce Type: cross Neural Ranking Models (NRMs) are central to modern information retrieval but remain highly vulnerable to adversarial manipulation. Existing attacks often rely on heuristics or surrogate models, limiting effectiveness and transferability. We propose CRAFT, a supervised framework for black-box adversarial rank attacks powered by large language models (LLMs