arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.08290cs.LGcs.AI
收藏

数据投毒对反事实解释的影响

The Effect of Data Poisoning on Counterfactual Explanations

Bielefeld University(比勒菲尔德大学);University of Cyprus(塞浦路斯大学);J.P. Morgan AI Research(摩根大通AI研究);Inria, Sophia Antipolis(法国国家信息与自动化研究所,索菲亚安蒂波利斯)

André Artelt, Shubham Sharma, Freddy Lecué, Barbara Hammer

AI总结:

本文形式化反事实解释中的数据投毒问题,提出通用投毒机制,并在配水管网事件检测及多种先进方法上验证其可提高追索成本且现有防御难以检测。

摘要:

反事实解释是一种被广泛用于检查黑箱系统预测的方法。它们可以通过建议如何改变输入以获得不同(即更有利)的系统输出的可执行修改,从而提供计算追索的机会。然而,近期研究指出,它们容易受到多种形式的操纵。本文研究反事实解释在数据投毒面前的脆弱性。我们在反事实解释情境中正式引入并研究数据投毒,以在三个不同层面提高追索成本:针对单个实例的局部层面、一组实例子集的子群体层面,或针对所有实例的全局层面。在此情境下,我们正式引入并刻画数据投毒,并由此推导和研究一种通用数据投毒机制。我们在解释配水管网事件检测这一关键现实应用中展示了此类数据投毒的影响。此外,我们开展了广泛的实证评估,证明最先进的反事实生成方法和工具箱容易受到此类数据投毒攻击。进一步地,我们发现现有防御方法无法检测出这些有毒样本。

英文摘要:

Counterfactual explanations are a widely used approach for examining the predictions of black-box systems. They can offer the opportunity for computational recourse by suggesting actionable changes on how to alter the input to obtain a different (i.e., more favorable) system output. However, recent studies have pointed out their susceptibility to various forms of manipulation. This work studies the vulnerability of counterfactual explanations to data poisoning. We formally introduce and investigate data poisoning in the context of counterfactual explanations for increasing the cost of recourse on three different levels: locally for a single instance, a sub-group of instances, or globally for all instances. In this context, we formally introduce and characterize data poisonings, from which we derive and investigate a general data poisoning mechanism. We demonstrate the impact of such data poisoning in the critical real-world application of explaining event detections in water distribution networks. Additionally, we conduct an extensive empirical evaluation, demonstrating that state-of-the-art counterfactual generation methods and toolboxes are vulnerable to such data poisoning. Furthermore, we find that existing defense methods fail to detect those poisonous samples.

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。

↑