# Statistical Collusion by Collectives on Learning Platforms

arXiv: https://arxiv.org/abs/2502.04879 · HTML: https://mlsanity.com/paper/2502.04879/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 23 references that are in the map.
- First posted on arXiv 7 Feb 2025.

## Builds on (most cited first, 15 of 15)

- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Strategic Classification](https://mlsanity.com/paper/1506.06980/) (2015)
- [Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning](https://mlsanity.com/paper/2205.01992/) (2022)
- [Who Leads and Who Follows in Strategic Classification?](https://mlsanity.com/paper/2106.12529/) (2021)
- [An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences](https://mlsanity.com/paper/2111.08429/) (2021)
- [Algorithmic Collective Action in Machine Learning](https://mlsanity.com/paper/2302.04262/) (2023)
- [Data Leverage: A Framework for Empowering the Public in its Relationship with Technology Companies](https://mlsanity.com/paper/2012.09995/) (2020)
- [Excess Capacity and Backdoor Poisoning](https://mlsanity.com/paper/2109.00685/) (2021)
- [Politics of Adversarial Machine Learning](https://mlsanity.com/paper/2002.05648/) (2020)
- [Demystifying Poisoning Backdoor Attacks from a Statistical Perspective](https://mlsanity.com/paper/2310.10780/) (2023)
- [The Role of Learning Algorithms in Collective Action](https://mlsanity.com/paper/2405.06582/) (2024)
- [Backdoor Smoothing: Demystifying Backdoor Attacks on Deep Neural Networks](https://mlsanity.com/paper/2006.06721/) (2020)
- [Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions](https://mlsanity.com/paper/2106.07214/) (2021)
- [Adversarial for Good? How the Adversarial ML Community's Values Impede Socially Beneficial Uses of Attacks](https://mlsanity.com/paper/2107.10302/) (2021)
- [Online Algorithmic Recourse by Collective Action](https://mlsanity.com/paper/2401.00055/) (2023)

## Built on by (most cited first, 6 of 6)

- [Explaining and Preventing Alignment Collapse in Iterative RLHF](https://mlsanity.com/paper/2605.04266/) (2026)
- [Minority Collective Action for User-Side Fairness](https://mlsanity.com/paper/2508.15374/) (2025)
- [Algorithmic Collective Action with Multiple Collectives](https://mlsanity.com/paper/2508.19149/) (2025)
- [Look-Ahead Reasoning on Learning Platforms](https://mlsanity.com/paper/2511.14745/) (2025)
- [Strategically Deceptive Model Deployment in Performative Prediction](https://mlsanity.com/paper/2506.09044/) (2025)
- [A Statistical Framework for Algorithmic Collective Action with Multiple Collectives](https://mlsanity.com/paper/2605.06749/) (2026)

## 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.