研究群体如何通过合谋修改数据影响学习平台决策。
Statistical Collusion by Collectives on Learning Platforms
- 提出理论框架分析集体行为对平台的影响机制。
- 实验验证在产品评价场景中合谋可显著改变平台结果。
- 适合关注平台安全与数据可信度的研究者阅读。
随着平台越来越多依赖学习算法，群体可能为自身利益形成合谋，通过协同提交修改过的数据来影响平台。为评估此类行为的潜在影响，必须理解群体在行动前需进行的预判计算：既要评估集体行为的后果，又要避免因数据修改带来的风险。同时，还需设计基于可观测数据可推断量的可执行协调算法。本文构建了理论与算法相结合的框架，并在产品评价领域进行了实验验证。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。