Model-Agnostic Utility-Preserving Biometric Information Anonymization (2405.15062v1)
Abstract: The recent rapid advancements in both sensing and machine learning technologies have given rise to the universal collection and utilization of people's biometrics, such as fingerprints, voices, retina/facial scans, or gait/motion/gestures data, enabling a wide range of applications including authentication, health monitoring, or much more sophisticated analytics. While providing better user experiences and deeper business insights, the use of biometrics has raised serious privacy concerns due to their intrinsic sensitive nature and the accompanying high risk of leaking sensitive information such as identity or medical conditions. In this paper, we propose a novel modality-agnostic data transformation framework that is capable of anonymizing biometric data by suppressing its sensitive attributes and retaining features relevant to downstream machine learning-based analyses that are of research and business values. We carried out a thorough experimental evaluation using publicly available facial, voice, and motion datasets. Results show that our proposed framework can achieve a \highlight{high suppression level for sensitive information}, while at the same time retain underlying data utility such that subsequent analyses on the anonymized biometric data could still be carried out to yield satisfactory accuracy.
- Apple. Vision framework: Apply computer vision algorithms to perform a variety of tasks on input images and video. https://developer.apple.com/documentation/vision, 2021.
- Iris deidentification with high visual realism for privacy protection on websites and social networks. IEEE Access, 9:131995–132010, 2021. 2169-3536.
- Interpreting and explaining deep neural networks for classification of audio signals. CoRR, abs/1807.03418, 2018.
- Leo Breiman. Random forests. Machine learning, 2001.
- Privacy preserving face recognition utilizing differential privacy. Computers & Security, 97:101951, 2020.
- k-Anonymity. In T. Yu and S. Jajodia, editors, Secure Data Management in Decentralized Systems. Springer-Verlag, 2007.
- Survey of security and privacy issues on biometric system. In Handbook of Computer Networks and Cyber Security, pages 763–776. Springer, 2020.
- Data privacy: Definitions and techniques. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 20(6):793–817, December 2012.
- Biometric privacy protection: guidelines and technologies. In M. S. Obaidat, J.S. Sevillano, and F. Joaquim, editors, Communications in Computer and Information Science, volume 314, pages 3–19. Springer, 2012. 978-3-642-35754-1.
- The algorithmic foundations of differential privacy. Foundations and Trends® in Theoretical Computer Science, 9(3–4):211–407, 2014.
- Challenges in representation learning: A report on three machine learning contests. In NIPS, 2013.
- Integrating utility into face de-identification. In PET, 2005.
- Semi-supervised learning of multi-factor models for face de-identification. In CVPR, 2008.
- Generalized fisher score for feature selection. In Proceedings of the Twenty-Seventh Conference on Uncertainty in Artificial Intelligence, UAI’11, page 266–273, Arlington, Virginia, USA, 2011. AUAI Press.
- A survey on statistical, information, and estimation—theoretic views on privacy. IEEE BITS the Information Theory Magazine, 1(1):45–56, 2021.
- Hubert: Self-supervised speech representation learning by masked prediction of hidden units. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29:3451–3460, 2021.
- t𝑡titalic_t-closeness: Privacy beyond k𝑘kitalic_k-anonymity and ℓℓ\ellroman_ℓ-diversity. In ICDE, 2007.
- Anonymousnet: Natural face de-identification with measurable privacy. In CVPR Workshops, 2019.
- Deep learning face attributes in the wild. In ICCV, 2015.
- ℓℓ\ellroman_ℓ-diversity: Privacy beyond k𝑘kitalic_k-anonymity. ACM TKDD, 2007.
- Mobile sensor data anonymization. In Proceedings of the International Conference on Internet of Things Design and Implementation, IoTDI ’19, pages 49–58, New York, NY, USA, 2019. ACM.
- κ𝜅\kappaitalic_κ-same-net: neural-network-based face deidentification. In IWOBI, 2017.
- Utility-preserving biometric information anonymization. In European Symposium on Research in Computer Security, pages 24–41. Springer, 2022.
- Preserving privacy by de-identifying face images. IEEE TKDE, 2005.
- Survey of biometric pattern recognition via machine learning techniques. Contemporary Engineering Sciences, 11(34):1677–1694, 2018.
- K-same-siamese-gan: K-same algorithm with generative adversarial network for facial image de-identification with hyperparameter tuning and mixed precision training. In AVSS, 2019.
- Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 2011.
- De-identification for privacy protection in multimedia content. Image Commun., 2016.
- Infinite feature selection. In 2015 IEEE International Conference on Computer Vision (ICCV), pages 4202–4210, 2015.
- Brian C. Ross. Mutual information between discrete and continuous data sets. PLOS ONE, 9(2):1–5, 02 2014.
- A survey on biometric authentication: Toward secure and privacy-preserving identification. IEEE access, 7:5994–6009, 2018.
- Pierangela Samarati. Protecting Respondents’ Identities in Microdata Release. IEEE Transactions on Knowledge and Data Engineering (TKDE), 13(6):1010–1027, November/December 2001.
- Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015.
- Distinguishable de-identified faces. In FG, 2015.