Privacy against Real-Time Speech Emotion Detection via Acoustic Adversarial Evasion of Machine Learning

TL;DR

This paper introduces DARE-GP, a real-time, acoustic adversarial method that masks users' emotional information in speech to protect privacy against unseen speech emotion recognition systems, while preserving speech transcription accuracy.

Contribution

DARE-GP is a novel genetic programming-based approach that generates universal adversarial audio perturbations for real-time privacy protection in acoustic environments.

Findings

Effective in real-time on unseen utterances

Protects against black-box SER classifiers

Maintains speech transcription accuracy

Abstract

Smart speaker voice assistants (VAs) such as Amazon Echo and Google Home have been widely adopted due to their seamless integration with smart home devices and the Internet of Things (IoT) technologies. These VA services raise privacy concerns, especially due to their access to our speech. This work considers one such use case: the unaccountable and unauthorized surveillance of a user's emotion via speech emotion recognition (SER). This paper presents DARE-GP, a solution that creates additive noise to mask users' emotional information while preserving the transcription-relevant portions of their speech. DARE-GP does this by using a constrained genetic programming approach to learn the spectral frequency traits that depict target users' emotional content, and then generating a universal adversarial audio perturbation that provides this privacy protection. Unlike existing works, DARE-GP provides: a) real-time protection of previously unheard utterances, b) against previously unseen black-box SER classifiers, c) while protecting speech transcription, and d) does so in a realistic, acoustic environment. Further, this evasion is robust against defenses employed by a knowledgeable adversary. The evaluations in this work culminate with acoustic evaluations against two off-the-shelf commercial smart speakers using a small-form-factor (raspberry pi) integrated with a wake-word system to evaluate the efficacy of its real-world, real-time deployment.