LLMs power new adversarial attacks on neural ranking models

Researchers have developed a new framework called CRAFT to attack neural ranking models used in information retrieval. This framework utilizes large language models to generate adversarial content, which is then used to fine-tune and optimize the ranking models. Experiments demonstrated that CRAFT significantly improves adversarial promotion rates and rank boosts across various ranking architectures, highlighting potential vulnerabilities in real-world retrieval systems. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Highlights potential vulnerabilities in information retrieval systems due to generative AI, prompting the need for more robust defenses.

RANK_REASON This is a research paper detailing a new framework for attacking neural ranking models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• CRAFT
• LLM
• MS MARCO
• TREC Deep Learning 2019
• TREC Deep Learning 2020
• arXiv

• paper
• safety