Prada: Practical black-box adversarial attacks against neural ranking models
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 …
with pre-trained language models. However, deep neural models are notorious for their …
Order-disorder: Imitation adversarial attacks for black-box neural ranking models
Neural text ranking models have witnessed significant advancement and are increasingly
being deployed in practice. Unfortunately, they also inherit adversarial vulnerabilities of …
being deployed in practice. Unfortunately, they also inherit adversarial vulnerabilities of …
Topic-oriented adversarial attacks against black-box neural ranking models
Neural ranking models (NRMs) have attracted considerable attention in information retrieval.
Unfortunately, NRMs may inherit the adversarial vulnerabilities of general neural networks …
Unfortunately, NRMs may inherit the adversarial vulnerabilities of general neural networks …
Explainable information retrieval: A survey
Explainable information retrieval is an emerging research area aiming to make transparent
and trustworthy information retrieval systems. Given the increasing use of complex machine …
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 …
authors with ranking incentives: their goal is to promote their documents in rankings induced …
Towards Imperceptible Document Manipulations against Neural Ranking Models
Adversarial attacks have gained traction in order to identify potential vulnerabilities in neural
ranking models (NRMs), but current attack methods often introduce grammatical errors …
ranking models (NRMs), but current attack methods often introduce grammatical errors …
Dealing with textual noise for robust and effective BERT re-ranking
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 …
in two-phases ranking pipeline for information retrieval (IR). Meanwhile, recent studies have …
Certified robustness to word substitution ranking attack for neural ranking models
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 …
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
Recent advances in neural information retrieval (IR) models have significantly enhanced
their effectiveness over various IR tasks. The robustness of these models, essential for …
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 …
opt to have their documents highly ranked for queries of interest. Consequently, they often …