mlsanityData to 13 Oct 2026

Statistical Collusion by Collectives on Learning Platforms

arXiv 2502.04879 ↗First posted 7 Feb 2025stat.ML cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

As platforms increasingly rely on learning algorithms, collectives may form and seek ways to influence these platforms to align with their own interests. This can be achieved by coordinated submission of altered data. To evaluate the potential impact of such behavior, it is essential to understand the computations that collectives must perform to impact platforms in this way. In particular, collectives need to make a priori assessments of the effect of the collective before taking action, as they may face potential risks when modifying their data. Moreover they need to develop implementable coordination algorithms based on quantities that can be inferred from observed data. We develop a framework that provides a theoretical and algorithmic treatment of these issues and present experimental results in a product evaluation domain.

Key facts. Cited by 6 papers in the map (data through 13 Oct 2026). Builds on 15 of its 23 references that are in the map. First posted on arXiv 7 Feb 2025.

Builds on

15 of 23 references.

References · 15

  1. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,047
  2. 2015Strategic Classificationcited by 257
  3. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
  4. 2021Who Leads and Who Follows in Strategic Classification?cited by 53
  5. 2021An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defencescited by 42
  6. 2023Algorithmic Collective Action in Machine Learningcited by 31
  7. 2020Data Leverage: A Framework for Empowering the Public in its Relationship with Technology Companiescited by 26
  8. 2021Excess Capacity and Backdoor Poisoningcited by 24
  9. 2020Politics of Adversarial Machine Learningcited by 12
  10. 2023Demystifying Poisoning Backdoor Attacks from a Statistical Perspectivecited by 10
  11. 2024The Role of Learning Algorithms in Collective Actioncited by 8
  12. 2020Backdoor Smoothing: Demystifying Backdoor Attacks on Deep Neural Networkscited by 5
3 more
  1. 2021Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functionscited by 5
  2. 2021Adversarial for Good? How the Adversarial ML Community's Values Impede Socially Beneficial Uses of Attackscited by 5
  3. 2023Online Algorithmic Recourse by Collective Actioncited by 3

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2026Explaining and Preventing Alignment Collapse in Iterative RLHFcited by 4
  2. 2025Minority Collective Action for User-Side Fairnesscited by 3
  3. 2025Algorithmic Collective Action with Multiple Collectivescited by 2
  4. 2025Look-Ahead Reasoning on Learning Platformscited by 2
  5. 2025Strategically Deceptive Model Deployment in Performative Predictioncited by 0
  6. 2026A Statistical Framework for Algorithmic Collective Action with Multiple Collectivescited by 0