具有激励的对手：对抗鲁棒性的一种策略性替代方案
Adversaries With Incentives: A Strategic Alternative to Adversarial Robustness
AI总结：
本文提出策略训练框架，将对手视为追求自身激励的理性主体，并利用激励不确定性集合替代最坏情况对抗假设，实验表明轻微激励知识即可带来收益。
摘要：
对抗训练旨在防御对手：即那些唯一目标是以任何可能方式损害预测性能的恶意敌手。这呈现了一种相当严苛的视角，我们断言这会导致不必要的保守训练。作为替代，我们提出将对手建模为仅仅追求其自身目标——而不是直接与分类器作对。借助策略建模中的工具，我们的方法使得关于对手可能激励的知识或信念能够被用作学习的归纳偏置。因此，我们的策略训练方法被设计用于防御“激励不确定性集合”内的所有对手。当该集合达到最大时，该方法会诉诸对抗学习；而当该集合能够被适当地缩小时，则可提供潜在收益。我们开展了一系列实验，结果表明，即使是关于对手激励的轻微知识也可能有用，并且潜在收益的程度取决于这些激励如何与学习任务的结构相关联。
英文摘要：
Adversarial training aims to defend against adversaries: malicious opponents whose sole aim is to harm predictive performance in any way possible. This presents a rather harsh perspective, which we assert results in unnecessarily conservative training. As an alternative, we propose to model opponents as simply pursuing their own goals--rather than working directly against the classifier. Employing tools from strategic modeling, our approach enables knowledge or beliefs regarding the opponent's possible incentives to be used as inductive bias for learning. Accordingly, our method of strategic training is designed to defend against all opponents within an 'incentive uncertainty set'. This resorts to adversarial learning when the set is maximal, but offers potential gains when the set can be appropriately reduced. We conduct a series of experiments that show how even mild knowledge regarding the opponent's incentives can be useful, and that the degree of potential gains depends on how these incentives relate to the structure of the learning task.
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。
