Saved in:
Bibliographic Details
Main Authors: Ge, Wanying, Patino, Jose, Todisco, Massimiliano, Evans, Nicholas
Format: Preprint
Published: 2021
Subjects:
Online Access:https://arxiv.org/abs/2110.03309
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916223273402368
author Ge, Wanying
Patino, Jose
Todisco, Massimiliano
Evans, Nicholas
author_facet Ge, Wanying
Patino, Jose
Todisco, Massimiliano
Evans, Nicholas
contents Substantial progress in spoofing and deepfake detection has been made in recent years. Nonetheless, the community has yet to make notable inroads in providing an explanation for how a classifier produces its output. The dominance of black box spoofing detection solutions is at further odds with the drive toward trustworthy, explainable artificial intelligence. This paper describes our use of SHapley Additive exPlanations (SHAP) to gain new insights in spoofing detection. We demonstrate use of the tool in revealing unexpected classifier behaviour, the artefacts that contribute most to classifier outputs and differences in the behaviour of competing spoofing detection models. The tool is both efficient and flexible, being readily applicable to a host of different architecture models in addition to related, different applications. All results reported in the paper are reproducible using open-source software.
format Preprint
id arxiv_https___arxiv_org_abs_2110_03309
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Explaining deep learning models for spoofing and deepfake detection with SHapley Additive exPlanations
Ge, Wanying
Patino, Jose
Todisco, Massimiliano
Evans, Nicholas
Audio and Speech Processing
Substantial progress in spoofing and deepfake detection has been made in recent years. Nonetheless, the community has yet to make notable inroads in providing an explanation for how a classifier produces its output. The dominance of black box spoofing detection solutions is at further odds with the drive toward trustworthy, explainable artificial intelligence. This paper describes our use of SHapley Additive exPlanations (SHAP) to gain new insights in spoofing detection. We demonstrate use of the tool in revealing unexpected classifier behaviour, the artefacts that contribute most to classifier outputs and differences in the behaviour of competing spoofing detection models. The tool is both efficient and flexible, being readily applicable to a host of different architecture models in addition to related, different applications. All results reported in the paper are reproducible using open-source software.
title Explaining deep learning models for spoofing and deepfake detection with SHapley Additive exPlanations
topic Audio and Speech Processing
url https://arxiv.org/abs/2110.03309