arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.02659cs.GTcs.LG
收藏

对ML模型中重复迭代的博弈论理解

A Game-theoretic Understanding of Repeated Explanations in ML Models

Kavita Kumari, Murtuza Jadliwala, Sumit Kumar Jha, Anindya Maiti

摘要:

本文通过博弈论的方法,对由机器学习(ML)模型和相关解释方法组成的系统与寻求查询/输入的预测/标签及其解释的最终用户之间的策略性重复交互进行了形式化建模。在这个游戏中,恶意的最终用户必须从战略上决定何时停止查询并试图损害系统,而系统必须从战略上决定应该与最终用户共享多少信息(以嘈杂的解释形式)以及何时停止共享,所有这些都不知道最终用户的类型(诚实/恶意)。本文正式模型,这种权衡使用连续时间随机信号博弈框架,并在这样一个框架内的马尔可夫完美均衡状态的特点。

英文摘要:

This paper formally models the strategic repeated interactions between a system, comprising of a machine learning (ML) model and associated explanation method, and an end-user who is seeking a prediction/label and its explanation for a query/input, by means of game theory. In this game, a malicious end-user must strategically decide when to stop querying and attempt to compromise the system, while the system must strategically decide how much information (in the form of noisy explanations) it should share with the end-user and when to stop sharing, all without knowing the type (honest/malicious) of the end-user. This paper formally models this trade-off using a continuous-time stochastic Signaling game framework and characterizes the Markov perfect equilibrium state within such a framework.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑