Quantum-Inspired Audio Unlearning: Towards Privacy-Preserving Voice Biometrics

TL;DR

This paper introduces QPAudioEraser, a quantum-inspired framework for effectively erasing specific voice signatures from biometric models, ensuring privacy compliance with minimal impact on overall model performance.

Contribution

The paper presents a novel quantum-inspired audio unlearning method that addresses the limitations of existing techniques in handling sequential and high-dimensional audio data.

Findings

Achieves complete erasure of target voice data with 0% Forget Accuracy.

Maintains model utility with only 0.05% performance degradation.

Outperforms traditional baselines across various datasets and scenarios.

Abstract

The widespread adoption of voice-enabled authentication and audio biometric systems have significantly increased privacy vulnerabilities associated with sensitive speech data. Compliance with privacy regulations such as GDPR's right to be forgotten and India's DPDP Act necessitates targeted and efficient erasure of individual-specific voice signatures from already-trained biometric models. Existing unlearning methods designed for visual data inadequately handle the sequential, temporal, and high-dimensional nature of audio signals, leading to ineffective or incomplete speaker and accent erasure. To address this, we introduce QPAudioEraser, a quantum-inspired audio unlearning framework. Our our-phase approach involves: (1) weight initialization using destructive interference to nullify target features, (2) superposition-based label transformations that obscure class identity, (3) an uncertainty-maximizing quantum loss function, and (4) entanglement-inspired mixing of correlated weights to retain model knowledge. Comprehensive evaluations with ResNet18, ViT, and CNN architectures across AudioMNIST, Speech Commands, LibriSpeech, and Speech Accent Archive datasets validate QPAudioEraser's superior performance. The framework achieves complete erasure of target data (0% Forget Accuracy) while incurring minimal impact on model utility, with a performance degradation on retained data as low as 0.05%. QPAudioEraser consistently surpasses conventional baselines across single-class, multi-class, sequential, and accent-level erasure scenarios, establishing the proposed approach as a robust privacy-preserving solution.