Privacy-preserving Voice Analysis via Disentangled Representations

Abstract

Voice User Interfaces (VUIs) are increasingly popular and built into smartphones, home assistants, and Internet of Things (IoT) devices. Despite offering an always-on convenient user experience, VUIs raise new security and privacy concerns for their users. In this paper, we focus on attribute inference attacks in the speech domain, demonstrating the potential for an attacker to accurately infer a target user's sensitive and private attributes (e.g. their emotion, sex, or health status) from deep acoustic models. To defend against this class of attacks, we design, implement, and evaluate a user-configurable, privacy-aware framework for optimizing speech-related data sharing mechanisms. Our objective is to enable primary tasks such as speech recognition and user identification, while removing sensitive attributes in the raw speech data before sharing it with a cloud service provider. We leverage disentangled representation learning to explicitly learn independent factors in the raw data. Based on a user's preferences, a supervision signal informs the filtering out of invariant factors while retaining the factors reflected in the selected preference. Our experimental evaluation over five datasets shows that the proposed framework can effectively defend against attribute inference attacks by reducing their success rates to approximately that of guessing at random, while maintaining accuracy in excess of 99% for the tasks of interest. We conclude that negotiable privacy settings enabled by disentangled representations can bring new opportunities for privacy-preserving applications.

14 pages, 7 figures, 2020 Cloud Computing Security Workshop (CCSW'20) in conjunction with the ACM Conference on Computer and Communications Security (CCS)

References in corpus (7)

• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• Technical Privacy Metrics: a Systematic Survey
• vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations
• Mobile Sensor Data Anonymization
• I Know What You See: Power Side-Channel Attack on Convolutional Neural Network Accelerators
• Unsupervised Representation Disentanglement using Cross Domain Features and Adversarial Learning in Variational Autoencoder based Voice Conversion
• Unsupervised feature learning for speech using correspondence and Siamese networks

Cited by in corpus (6)

• The VoicePrivacy 2020 Challenge: Results and findings
• Towards Battery-Free Machine Learning and Inference in Underwater Environments
• Privacy against Real-Time Speech Emotion Detection via Acoustic Adversarial Evasion of Machine Learning
• Privacy-Protecting Techniques for Behavioral Biometric Data: A Survey
• Privacy-oriented manipulation of speaker representations
• Beyond Neural-on-Neural Approaches to Speaker Gender Protection