attack arXiv Sep 26, 2025 · Sep 2025
Sameep Chattopadhyay, Nikhil Karamchandani, Sharayu Moharir · University of Washington · Indian Institute of Technology Bombay
Attacks online learning-to-rank algorithms via observation-free click-feedback manipulation to promote target items and induce linear regret with only O(log T) manipulations
Model Skewing reinforcement-learning
Online learning to rank (OLTR) plays a critical role in information retrieval and machine learning systems, with a wide range of applications in search engines and content recommenders. However, despite their extensive adoption, the susceptibility of OLTR algorithms to coordinated adversarial attacks remains poorly understood. In this work, we present a novel framework for attacking some of the widely used OLTR algorithms. Our framework is designed to promote a set of target items so that they appear in the list of top-K recommendations for T - o(T) rounds, while simultaneously inducing linear regret in the learning algorithm. We propose two novel attack strategies: CascadeOFA for CascadeUCB1 and PBMOFA for PBM-UCB . We provide theoretical guarantees showing that both strategies require only O(log T) manipulations to succeed. Additionally, we supplement our theoretical analysis with empirical results on real-world data.
traditional_ml rl University of Washington · Indian Institute of Technology Bombay
ML Security Papers