Privacy-preserving Voice Analysis via Disentangled Representations

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.

[1]  Jae Lim,et al.  Signal estimation from modified short-time Fourier transform , 1984 .

[2]  Gregory H. Wakefield,et al.  Chromagram visualization of the singing voice , 1999, MAVEBA.

[3]  Hideki Kawahara,et al.  STRAIGHT, exploitation of the other aspect of VOCODER: Perceptually isomorphic decomposition of speech sounds , 2006 .

[4]  James D. Edge,et al.  Audio-visual feature selection and reduction for emotion classification , 2008, AVSP.

[5]  Carlos Busso,et al.  IEMOCAP: interactive emotional dyadic motion capture database , 2008, Lang. Resour. Evaluation.

[6]  Shrikanth S. Narayanan,et al.  On the robustness of overall F0-only modifications to the perception of emotions in speech. , 2008, The Journal of the Acoustical Society of America.

[7]  Jan Paul Kolter.  User-centric privacy: a usable and provider-independent privacy infrastructure , 2010 .

[8]  Carmela Troncoso,et al.  Protecting location privacy: optimal strategy against localization attacks , 2012, CCS.

[9]  Yoshua Bengio,et al.  Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation , 2013, ArXiv.

[10]  Erich Elsen,et al.  Deep Speech: Scaling up end-to-end speech recognition , 2014, ArXiv.

[11]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[12]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[13]  Yuting Zhang,et al.  Learning to Disentangle Factors of Variation with Manifold Interaction , 2014, ICML.

[14]  Sanjeev Khudanpur,et al.  Librispeech: An ASR corpus based on public domain audio books , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[15]  Joshua B. Tenenbaum,et al.  Deep Convolutional Inverse Graphics Network , 2015, NIPS.

[16]  Giovanni Felici,et al.  Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers , 2013, Int. J. Secur. Networks.

[17]  Quoc V. Le,et al.  Listen, attend and spell: A neural network for large vocabulary conversational speech recognition , 2015, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[18]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[19]  Yann LeCun,et al.  Disentangling factors of variation in deep representation using adversarial training , 2016, NIPS.

[20]  Amos J. Storkey,et al.  Censoring Representations with an Adversary , 2015, ICLR.

[21]  Chong Wang,et al.  Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin , 2015, ICML.

[22]  Masanori Morise,et al.  WORLD: A Vocoder-Based High-Quality Speech Synthesis System for Real-Time Applications , 2016, IEICE Trans. Inf. Syst..

[23]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[24]  Vitaly Shmatikov,et al.  Machine Learning Models that Remember Too Much , 2017, CCS.

[25]  Hyunsoo Kim,et al.  Learning to Discover Cross-Domain Relations with Generative Adversarial Networks , 2017, ICML.

[26]  Joon Son Chung,et al.  VoxCeleb: A Large-Scale Speaker Identification Dataset , 2017, INTERSPEECH.

[27]  Guillaume Lample,et al.  Fader Networks: Manipulating Images by Sliding Attributes , 2017, NIPS.

[28]  Christopher Burgess,et al.  beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework , 2016, ICLR 2016.

[29]  Ersin Yumer,et al.  Neural Face Editing with Intrinsic Image Disentangling , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Yu Zhang,et al.  Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data , 2017, NIPS.

[31]  Vitaly Shmatikov,et al.  Membership Inference Attacks Against Machine Learning Models , 2016, 2017 IEEE Symposium on Security and Privacy (SP).

[32]  Oriol Vinyals,et al.  Neural Discrete Representation Learning , 2017, NIPS.

[33]  Christian Poellabauer,et al.  Towards Learning Fine-Grained Disentangled Representations from Speech , 2018, ArXiv.

[34]  Andriy Mnih,et al.  Disentangling by Factorising , 2018, ICML.

[35]  Yi-Hsuan Tsai,et al.  Domain Adaptation for Structured Output via Disentangled Patch Representations , 2018 .

[36]  Linlin Chen,et al.  Hidebehind: Enjoy Voice Input with Voiceprint Unclonability and Anonymity , 2018, SenSys.

[37]  Jinyuan Jia,et al.  AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning , 2018, USENIX Security Symposium.

[38]  Yusuke Ijima,et al.  DNN-Based Speech Synthesis Using Speaker Codes , 2018, IEICE Trans. Inf. Syst..

[39]  Jung-Woo Ha,et al.  StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[40]  Nikita Borisov,et al.  Property Inference Attacks on Fully Connected Neural Networks using Permutation Invariant Representations , 2018, CCS.

[41]  Bo Luo,et al.  I Know What You See: Power Side-Channel Attack on Convolutional Neural Network Accelerators , 2018, ACSAC.

[42]  Adam Roberts,et al.  Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models , 2017, ICLR.

[43]  Hidebehind , 2018, Proceedings of the 16th ACM Conference on Embedded Networked Sensor Systems.

[44]  S. R. Livingstone,et al.  The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English , 2018, PloS one.

[45]  Ming Li,et al.  Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System , 2018, Odyssey.

[46]  David Eckhoff,et al.  Metrics : a Systematic Survey , 2018 .

[47]  Rob Brekelmans,et al.  Invariant Representations without Adversarial Training , 2018, NeurIPS.

[48]  Toniann Pitassi,et al.  Learning Adversarially Fair and Transferable Representations , 2018, ICML.

[49]  Tara N. Sainath,et al.  State-of-the-Art Speech Recognition with Sequence-to-Sequence Models , 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[50]  Somesh Jha,et al.  Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting , 2017, 2018 IEEE 31st Computer Security Foundations Symposium (CSF).

[51]  Erich Elsen,et al.  Efficient Neural Audio Synthesis , 2018, ICML.

[52]  I-Fan Chen,et al.  End-to-end Anchored Speech Recognition , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[53]  Nicholas W. D. Evans,et al.  Preserving privacy in speaker and speech characterisation , 2019, Comput. Speech Lang..

[54]  Andrea Cavallaro,et al.  Mobile Sensor Data Anonymization , 2019 .

[55]  M. Liu,et al.  Group Retention when Using Machine Learning in Sequential Decision Making: the Interplay between User Dynamics and Fairness , 2019, NeurIPS.

[56]  Vitaly Shmatikov,et al.  Exploiting Unintended Feature Leakage in Collaborative Learning , 2018, 2019 IEEE Symposium on Security and Privacy (SP).

[57]  Hyung-Min Park,et al.  Unsupervised Speech Domain Adaptation Based on Disentangled Representation Learning for Robust Speech Recognition , 2019, ArXiv.

[58]  Toniann Pitassi,et al.  Flexibly Fair Representation Learning by Disentanglement , 2019, ICML.

[59]  Suresh Venkatasubramanian,et al.  Disentangling Influence: Using Disentangled Representations to Audit Model Predictions , 2019, NeurIPS.

[60]  Úlfar Erlingsson,et al.  The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks , 2018, USENIX Security Symposium.

[61]  Hamed Haddadi,et al.  Emotion Filtering at the Edge , 2019, SenSys-ML.

[62]  Thomas Drugman,et al.  Towards Achieving Robust Universal Neural Vocoding , 2018, INTERSPEECH.

[63]  Ronan Collobert,et al.  wav2vec: Unsupervised Pre-training for Speech Recognition , 2019, INTERSPEECH.

[64]  Stefan Bauer,et al.  On the Fairness of Disentangled Representations , 2019, NeurIPS.

[65]  Stefan Wermter,et al.  Predictive Auxiliary Variational Autoencoder for Representation Learning of Global Speech Characteristics , 2019, INTERSPEECH.

[66]  Zhen-Hua Ling,et al.  Learning Latent Representations for Style Control and Transfer in End-to-end Speech Synthesis , 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[67]  Joon Son Chung,et al.  Utterance-level Aggregation for Speaker Recognition in the Wild , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[68]  Kate Saenko,et al.  Domain Agnostic Learning with Disentangled Representations , 2019, ICML.

[69]  Bumsub Ham,et al.  Learning Disentangled Representation for Robust Person Re-identification , 2019, NeurIPS.

[70]  Shuicheng Yan,et al.  Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition , 2018, AAAI.

[71]  Amir Houmansadr,et al.  Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning , 2018, 2019 IEEE Symposium on Security and Privacy (SP).

[72]  Emily Mower Provost,et al.  Privacy Enhanced Multimodal Neural Representations for Emotion Recognition , 2019, AAAI.

[73]  Ashish Shrivastava,et al.  Unsupervised Style and Content Separation by Minimizing Mutual Information for Speech Synthesis , 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[74]  Rajib Rana,et al.  Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends , 2020, ArXiv.

[75]  Dan Jurafsky,et al.  Racial disparities in automated speech recognition , 2020, Proceedings of the National Academy of Sciences.

[76]  Seunghoon Hong,et al.  High-Fidelity Synthesis with Disentangled Representation , 2020, ECCV.

[77]  Yu-Huai Peng,et al.  Unsupervised Representation Disentanglement Using Cross Domain Features and Adversarial Learning in Variational Autoencoder Based Voice Conversion , 2020, IEEE Transactions on Emerging Topics in Computational Intelligence.

[78]  Daniel J. Dubois,et al.  When Speakers Are All Ears: Characterizing Misactivations of IoT Smart Speakers , 2020, Proc. Priv. Enhancing Technol..

[79]  Heiga Zen,et al.  Fully-Hierarchical Fine-Grained Prosody Modeling For Interpretable Speech Synthesis , 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[80]  Herman Kamper,et al.  Unsupervised Feature Learning for Speech Using Correspondence and Siamese Networks , 2020, IEEE Signal Processing Letters.

[81]  Alexei Baevski,et al.  vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations , 2019, ICLR.

[82]  Mhd Hasan Sarhan,et al.  Fairness by Learning Orthogonal Disentangled Representations , 2020, ECCV.

[83]  Joon Son Chung,et al.  In defence of metric learning for speaker recognition , 2020, INTERSPEECH.

[84]  Vitaly Shmatikov,et al.  Overlearning Reveals Sensitive Attributes , 2019, ICLR.

[85]  An empirical analysis of information encoded in disentangled neural speaker representations , 2020, Odyssey.