Towards Data Drift Monitoring for Speech Deepfake Detection in the context of MLOps

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xin, Ge, Wanying, Yamagishi, Junichi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909783621107712
author Wang, Xin
Ge, Wanying
Yamagishi, Junichi
author_facet Wang, Xin
Ge, Wanying
Yamagishi, Junichi
contents When being delivered in applications or services on the cloud, static speech deepfake detectors that are not updated will become vulnerable to newly created speech deepfake attacks. From the perspective of machine learning operations (MLOps), this paper tries to answer whether we can monitor new and unseen speech deepfake data that drifts away from a seen reference data set. We further ask, if drift is detected, whether we can fine-tune the detector using similarly drifted data, reduce the drift, and improve the detection performance. On a toy dataset and the large-scale MLAAD dataset, we show that the drift caused by new text-to-speech (TTS) attacks can be monitored using distances between the distributions of the new data and reference data. Furthermore, we demonstrate that fine-tuning the detector using data generated by the new TTS deepfakes can reduce the drift and the detection error rates.
format Preprint
id arxiv_https___arxiv_org_abs_2509_10086
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Data Drift Monitoring for Speech Deepfake Detection in the context of MLOps
Wang, Xin
Ge, Wanying
Yamagishi, Junichi
Audio and Speech Processing
When being delivered in applications or services on the cloud, static speech deepfake detectors that are not updated will become vulnerable to newly created speech deepfake attacks. From the perspective of machine learning operations (MLOps), this paper tries to answer whether we can monitor new and unseen speech deepfake data that drifts away from a seen reference data set. We further ask, if drift is detected, whether we can fine-tune the detector using similarly drifted data, reduce the drift, and improve the detection performance. On a toy dataset and the large-scale MLAAD dataset, we show that the drift caused by new text-to-speech (TTS) attacks can be monitored using distances between the distributions of the new data and reference data. Furthermore, we demonstrate that fine-tuning the detector using data generated by the new TTS deepfakes can reduce the drift and the detection error rates.
title Towards Data Drift Monitoring for Speech Deepfake Detection in the context of MLOps
topic Audio and Speech Processing
url https://arxiv.org/abs/2509.10086