Statistical Collusion by Collectives on Learning Platforms

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Gauthier, Etienne, Bach, Francis, Jordan, Michael I.
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918033017012224
author Gauthier, Etienne
Bach, Francis
Jordan, Michael I.
author_facet Gauthier, Etienne
Bach, Francis
Jordan, Michael I.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_04879
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Statistical Collusion by Collectives on Learning Platforms
Gauthier, Etienne
Bach, Francis
Jordan, Michael I.
Machine Learning
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.
title Statistical Collusion by Collectives on Learning Platforms
topic Machine Learning
url https://arxiv.org/abs/2502.04879