arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1910.00057cs.AI
收藏

用于修改模型决策的合成动作序列

Synthesizing Action Sequences for Modifying Model Decisions

University of Wisconsin - Madison(威斯康星大学麦迪逊分校)

Goutham Ramakrishnan, Yun Chan Lee, Aws Albarghouthi

摘要:

当一个模型做出一个重要的决定时,例如,拒绝某人的贷款,它需要额外产生可操作的,现实的反馈,关于这个人可以做些什么来有利地改变决定。我们通过程序合成的镜头来处理这个问题,我们的目标是合成一个最佳(实际上最便宜或最简单)的动作序列,如果一个人成功执行,就可以改变他们的分类。我们提出了一种新的和一般的方法,结合基于搜索的程序合成和测试时的对抗攻击,构建动作序列的一组特定领域的行动。我们证明了我们的方法在一些深度神经网络上的有效性。

英文摘要:

When a model makes a consequential decision, e.g., denying someone a loan, it needs to additionally generate actionable, realistic feedback on what the person can do to favorably change the decision. We cast this problem through the lens of program synthesis, in which our goal is to synthesize an optimal (realistically cheapest or simplest) sequence of actions that if a person executes successfully can change their classification. We present a novel and general approach that combines search-based program synthesis and test-time adversarial attacks to construct action sequences over a domain-specific set of actions. We demonstrate the effectiveness of our approach on a number of deep neural networks.

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。

↑