mlsanityData to 14 Oct 2026

Adversarial Attacks on Online Learning to Rank with Stochastic Click Models

arXiv 2305.19218 ↗First posted 30 May 2023cs.LG cs.CRcited by 6

Not on the map. Why?

Abstract (arXiv)

We propose the first study of adversarial attacks on online learning to rank. The goal of the adversary is to misguide the online learning to rank algorithm to place the target item on top of the ranking list linear times to time horizon T with a sublinear attack cost. We propose generalized list poisoning attacks that perturb the ranking list presented to the user. This strategy can efficiently attack any no-regret ranker in general stochastic click models. Furthermore, we propose a click poisoning-based strategy named attack-then-quit that can efficiently attack two representative OLTR algorithms for stochastic click models. We theoretically analyze the success and cost upper bound of the two proposed methods. Experimental results based on synthetic and real-world data further validate the effectiveness and cost-efficiency of the proposed attack strategies.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 25 of its 47 references that are in the map. First posted on arXiv 30 May 2023.

Builds on

25 of 47 references.

References · 25

  1. 2018Stochastic bandits robust to adversarial corruptionscited by 119
  2. 2015Cascading Bandits: Learning to Rank in the Cascade Modelcited by 77
  3. 2020Stochastic Linear Bandits Robust to Adversarial Attackscited by 65
  4. 2018Adversarial Attacks on Stochastic Banditscited by 57
  5. 2019Data Poisoning Attacks on Stochastic Banditscited by 53
  6. 2016Cascading Bandits for Large-Scale Recommendation Problemscited by 45
  7. 2015Combinatorial Cascading Banditscited by 40
  8. 2020Adversarial Attacks on Linear Contextual Banditscited by 34
  9. 2018TopRank: A practical algorithm for online stochastic rankingcited by 30
  10. 2016Multiple-Play Bandits in the Position-Based Modelcited by 28
  11. 2017Online Learning to Rank in Stochastic Click Modelscited by 26
  12. 2018Differentiable Unbiased Online Learning to Rankcited by 24
13 more
  1. 2018Online Learning to Rank with Featurescited by 18
  2. 2016DCM Bandits: Learning to Rank with Multiple Clickscited by 17
  3. 2020Learning Product Rankings Robust to Fake Userscited by 12
  4. 2021When Are Linear Stochastic Bandits Attackable?cited by 10
  5. 2022Minimax Regret for Cascading Banditscited by 10
  6. 2018Efficient Exploration of Gradient Space for Online Learning to Rankcited by 9
  7. 2019Variance Reduction in Gradient Exploration for Online Learning to Rankcited by 9
  8. 2016The Capacity of Robust Private Information Retrieval with Colluding Databasescited by 6
  9. 2021PairRank: Online Pairwise Learning to Rank by Divide-and-Conquercited by 6
  10. 2023Adversarial Attacks on Adversarial Banditscited by 6
  11. 2023Adversarial Attacks on Online Learning to Rank with Click Feedbackcited by 6
  12. 2021Adversarial Attacks on Gaussian Process Banditscited by 5
  13. 2021Efficient Action Poisoning Attacks on Linear Contextual Banditscited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 3.

6 papers.

  1. 2024Online Experimental Design With Estimation-Regret Trade-off Under Network Interferencecited by 9
  2. 2025Practical Adversarial Attacks on Stochastic Bandits via Fake Data Injectioncited by 3
  3. 2024Stealthy Adversarial Attacks on Stochastic Multi-Armed Banditscited by 2
  4. 2025Design-Based Bandits Under Network Interference: Trade-Off Between Regret and Statistical Inferencecited by 1
  5. 2023Adversarial Attacks on Cooperative Multi-agent Banditscited by 0
  6. 2025Observation-Free Attacks on Online Learning to Rankcited by 0