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 2208.09418cs.LGcs.AI
收藏

SAFARI:针对可解释性鲁棒性的通用且高效的评估

SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability

Purple Mountain Laboratories(紫金山实验室);University of Liverpool(利物浦大学);WMG, University of Warwick(华威大学制造工程学院);Institute of Software, CAS(中国科学院软件研究所)

Wei Huang, Xingyu Zhao, Gaojie Jin, Xiaowei Huang

AI总结:

本文提出SAFARI框架,通过遗传算法求解最坏情况解释差异和子集模拟评估整体鲁棒性概率,解决XAI解释鲁棒性评估的全面性、异构性和罕见事件挑战,其准确性、灵敏度和效率均优于现有方法。

摘要:

深度学习(DL)的可解释性是实现可信AI的障碍。尽管可解释AI(XAI)社区做出了巨大努力,但解释缺乏鲁棒性——难以区分的输入扰动可能导致不同的XAI结果。因此,在给定XAI方法的情况下,评估DL可解释性的鲁棒程度至关重要。本文指出了现有最先进方法无法共同应对的几个挑战:i)现有指标不够全面;ii)XAI技术高度异构;iii)误解释通常是罕见事件。为应对这些挑战,我们提出了两种黑盒评估方法,分别涉及最坏情况下的解释差异和一般情况下的鲁棒性概率概念。使用带有定制适应度函数的遗传算法(GA)求解约束优化,以实现高效的最坏情况评估。使用专门用于估计罕见事件概率的子集模拟(SS)来评估整体鲁棒性。实验表明,我们方法的准确性、灵敏度和效率均优于现有最先进方法。最后,我们展示了方法的两个应用:对鲁棒的XAI方法进行排序,以及选择训练方案以同时提升分类和解释的鲁棒性。

英文摘要:

Interpretability of Deep Learning (DL) is a barrier to trustworthy AI. Despite great efforts made by the Explainable AI (XAI) community, explanations lack robustness -- indistinguishable input perturbations may lead to different XAI results. Thus, it is vital to assess how robust DL interpretability is, given an XAI method. In this paper, we identify several challenges that the state-of-the-art is unable to cope with collectively: i) existing metrics are not comprehensive; ii) XAI techniques are highly heterogeneous; iii) misinterpretations are normally rare events. To tackle these challenges, we introduce two black-box evaluation methods, concerning the worst-case interpretation discrepancy and a probabilistic notion of how robust in general, respectively. Genetic Algorithm (GA) with bespoke fitness function is used to solve constrained optimisation for efficient worst-case evaluation. Subset Simulation (SS), dedicated to estimate rare event probabilities, is used for evaluating overall robustness. Experiments show that the accuracy, sensitivity, and efficiency of our methods outperform the state-of-the-arts. Finally, we demonstrate two applications of our methods: ranking robust XAI methods and selecting training schemes to improve both classification and interpretation robustness.

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。

↑