The Library
SAFARI : Versatile and efficient evaluations for robustness of interpretability
Tools
Huang, Wei, Zhao, Xingyu, Jin, Gaojie and Huang, Xiaowei (2023) SAFARI : Versatile and efficient evaluations for robustness of interpretability. In: International Conference on Computer Vision 2023, Paris, 02-06 Oct 2023 (In Press)
PDF
WRAP-SAFARI-versatile-efficient-evaluations-robustness-interpretability-23.pdf - Accepted Version Embargoed item. Restricted access to Repository staff only - Requires a PDF viewer. Download (6Mb) |
Abstract
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 worstcase 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-ofthe-arts. Finally, we demonstrate two applications of our methods: ranking robust XAI methods and selecting training schemes to improve both classification and interpretation robustness.
Item Type: | Conference Item (Paper) | ||||||
---|---|---|---|---|---|---|---|
Subjects: | Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software | ||||||
Divisions: | Faculty of Science, Engineering and Medicine > Engineering > WMG (Formerly the Warwick Manufacturing Group) | ||||||
Official Date: | 2023 | ||||||
Dates: |
|
||||||
Status: | Peer Reviewed | ||||||
Publication Status: | In Press | ||||||
Access rights to Published version: | Restricted or Subscription Access | ||||||
Date of first compliant deposit: | 14 July 2023 | ||||||
Conference Paper Type: | Paper | ||||||
Title of Event: | International Conference on Computer Vision 2023 | ||||||
Type of Event: | Conference | ||||||
Location of Event: | Paris | ||||||
Date(s) of Event: | 02-06 Oct 2023 | ||||||
Related URLs: | |||||||
Open Access Version: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |