Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-Box Neural Ranking Models
Year: 2025
Type: conference-paper
Abstract: Neural ranking models (NRMs) have been shown to be highly effective in terms of retrieval performance. Unfortunately, they have also displayed a higher degree of sensitivity to attacks than previous generation models. To help expose and address this lack of robustness, we introduce a novel ranking attack framework named Attack-in-the-Chain, which tracks interactions between large language models (LLMs) and NRMs based on chain-of-thought (CoT) prompting to generate adversarial examples under black-box settings. Our approach starts by identifying anchor documents with higher ranking positions than the target document as nodes in the reasoning chain. We then dynamically assign the number of perturbation words to each node and prompt LLMs to execute attacks. Finally, we verify the attack performance of all nodes at each reasoning step and proceed to generate the next reasoning step. Empirical results on two web search benchmarks show the effectiveness of our method.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
Funders: European Commission, National Natural Science Foundation of China, Nederlandse Organisatie voor Wetenschappelijk Onderzoek, Youth Innovation Promotion Association of the Chinese Academy of Sciences, HORIZON EUROPE Framework Programme, National Key Research and Development Program of China, Youth Innovation Promotion Association
OpenAlex ID: W4409364811