面向已部署深度伪造语音检测器的无监督数据漂移监控

View PDF HTML (experimental)

Abstract:Deepfake speech detectors are typically evaluated as binary classifiers on fixed benchmarks, but deployed systems face evolving attacks, codecs, speakers, and recording conditions, with labels unavailable during operation. This makes it difficult to know when a detector operates in familiar conditions and can be relied on. We propose an unsupervised drift monitor that operates on the internal embeddings of a deployed detector. The monitor compares each input against bona fide and spoof references using regularized Mahalanobis distances. These distances define trusted, ambiguous, and novel regions of the detector embedding space, allowing unfamiliar inputs to be routed for review. We evaluate the monitor on four modern detectors on three datasets. The monitor raises alerts for dataset mismatches and substantially reduces the security-critical case of accepting deepfakes at the cost of reduced automatic coverage. The results also show that drift affects both classes: bona fide recordings can move away from the training reference, increasing alert rates even in in-domain settings. Our findings suggest that deployed deepfake speech detectors should be treated not only as a binary classification, but also as a reliability problem.

Comments:	Accepted at IEEE International Workshop on Information Forensics and Security (WIFS) 2026
Subjects:	Sound (cs.SD); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
Cite as:	arXiv:2610.16826 [cs.SD]
	(or arXiv:2610.16826v1 [cs.SD] for this version)
	https://doi.org/10.48550/arXiv.2610.16826 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Vojtěch Staněk [view email]
[v1] Mon, 12 Oct 2026 14:08:25 UTC (314 KB)