Explainable deepfake and spoofing detection: an attack analysis using SHapley Additive exPlanations

02/28/2022
by   Wanying Ge, et al.
0

Despite several years of research in deepfake and spoofing detection for automatic speaker verification, little is known about the artefacts that classifiers use to distinguish between bona fide and spoofed utterances. An understanding of these is crucial to the design of trustworthy, explainable solutions. In this paper we report an extension of our previous work to better understand classifier behaviour to the use of SHapley Additive exPlanations (SHAP) to attack analysis. Our goal is to identify the artefacts that characterise utterances generated by different attacks algorithms. Using a pair of classifiers which operate either upon raw waveforms or magnitude spectrograms, we show that visualisations of SHAP results can be used to identify attack-specific artefacts and the differences and consistencies between synthetic speech and converted voice spoofing attacks.

READ FULL TEXT

page 3

page 5

research
10/02/2022

Voice Spoofing Countermeasures: Taxonomy, State-of-the-art, experimental analysis of generalizability, open challenges, and the way forward

Malicious actors may seek to use different voice-spoofing attacks to foo...
research
04/14/2020

An explainability study of the constant Q cepstral coefficient spoofing countermeasure for automatic speaker verification

Anti-spoofing for automatic speaker verification is now a well establish...
research
05/20/2020

Spoofing Attack Detection using the Non-linear Fusion of Sub-band Classifiers

The threat of spoofing can pose a risk to the reliability of automatic s...
research
10/10/2016

Investigation of Synthetic Speech Detection Using Frame- and Segment-Specific Importance Weighting

Speaker verification systems are vulnerable to spoofing attacks which pr...
research
09/19/2023

Bridging the Spoof Gap: A Unified Parallel Aggregation Network for Voice Presentation Attacks

Automatic Speaker Verification (ASV) systems are increasingly used in vo...
research
06/11/2021

Visualizing Classifier Adjacency Relations: A Case Study in Speaker Verification and Voice Anti-Spoofing

Whether it be for results summarization, or the analysis of classifier f...
research
01/04/2019

Introduction to Voice Presentation Attack Detection and Recent Advances

Over the past few years significant progress has been made in the field ...

Please sign up or login with your details

Forgot password? Click here to reset