Prada: Practical black-box adversarial attacks against neural ranking models

C Wu, R Zhang, J Guo, M De Rijke, Y Fan… - ACM Transactions on …, 2023 - dl.acm.org
Neural ranking models (NRMs) have shown remarkable success in recent years, especially
with pre-trained language models. However, deep neural models are notorious for their …

Order-disorder: Imitation adversarial attacks for black-box neural ranking models

J Liu, Y Kang, D Tang, K Song, C Sun, X Wang… - Proceedings of the …, 2022 - dl.acm.org
Neural text ranking models have witnessed significant advancement and are increasingly
being deployed in practice. Unfortunately, they also inherit adversarial vulnerabilities of …

Topic-oriented adversarial attacks against black-box neural ranking models

YA Liu, R Zhang, J Guo, M de Rijke, W Chen… - Proceedings of the 46th …, 2023 - dl.acm.org
Neural ranking models (NRMs) have attracted considerable attention in information retrieval.
Unfortunately, NRMs may inherit the adversarial vulnerabilities of general neural networks …

Explainable information retrieval: A survey

A Anand, L Lyu, M Idahl, Y Wang, J Wallat… - arXiv preprint arXiv …, 2022 - arxiv.org
Explainable information retrieval is an emerging research area aiming to make transparent
and trustworthy information retrieval systems. Given the increasing use of complex machine …

Competitive search

O Kurland, M Tennenholtz - Proceedings of the 45th International ACM …, 2022 - dl.acm.org
The Web is a canonical example of a competitive search setting that includes document
authors with ranking incentives: their goal is to promote their documents in rankings induced …

Towards Imperceptible Document Manipulations against Neural Ranking Models

X Chen, B He, Z Ye, L Sun, Y Sun - arXiv preprint arXiv:2305.01860, 2023 - arxiv.org
Adversarial attacks have gained traction in order to identify potential vulnerabilities in neural
ranking models (NRMs), but current attack methods often introduce grammatical errors …

Dealing with textual noise for robust and effective BERT re-ranking

X Chen, B He, K Hui, L Sun, Y Sun - Information Processing & …, 2023 - Elsevier
The pre-trained language models (PLMs), such as BERT, have been successfully employed
in two-phases ranking pipeline for information retrieval (IR). Meanwhile, recent studies have …

Certified robustness to word substitution ranking attack for neural ranking models

C Wu, R Zhang, J Guo, W Chen, Y Fan… - Proceedings of the 31st …, 2022 - dl.acm.org
Neural ranking models (NRMs) have achieved promising results in information retrieval.
NRMs have also been shown to be vulnerable to adversarial examples. A typical Word …

Robust neural information retrieval: An adversarial and out-of-distribution perspective

YA Liu, R Zhang, J Guo, M de Rijke, Y Fan… - arXiv preprint arXiv …, 2024 - arxiv.org
Recent advances in neural information retrieval (IR) models have significantly enhanced
their effectiveness over various IR tasks. The robustness of these models, essential for …

Content-Based Relevance Estimation in Retrieval Settings with Ranking-Incentivized Document Manipulations

Z Vasilisky, O Kurland, M Tennenholtz… - Proceedings of the 2023 …, 2023 - dl.acm.org
In retrieval settings such as the Web, many document authors are ranking incentivized: they
opt to have their documents highly ranked for queries of interest. Consequently, they often …