@article{1187147063c04efb97cbdf65c5f236a1,
title = "SecureFace: Face Template Protection",
abstract = "It has been shown that face images can be reconstructed from their representations (templates). We propose a randomized CNN to generate protected face biometric templates given the input face image and a user-specific key. The use of user-specific keys introduces randomness to the secure template and hence strengthens the template security. To further enhance the security of the templates, instead of storing the key, we store a secure sketch that can be decoded to generate the key with genuine queries submitted to the system. We have evaluated the proposed protected template generation method using three benchmarking datasets for the face (FRGC v2.0, CFP, and IJB-A). The experimental results justify that the protected template generated by the proposed method are non-invertible and cancellable, while preserving the verification performance.",
keywords = "Biometric, deep templates, protected templates, randomized CNN, template protection, template security",
author = "Guangcan Mai and Kai Cao and Xiangyuan Lan and Yuen, {Pong Chi}",
note = "Funding Information: Manuscript received December 28, 2019; revised April 19, 2020 and June 9, 2020; accepted July 6, 2020. Date of publication July 15, 2020; date of current version July 31, 2020. This work was supported in part by the Hong Kong RGC under Grant HKBU 12200820. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. Raymond Veldhuis. (Corresponding author: Pong C. Yuen.) Guangcan Mai was with the Department of Computer Science, Hong Kong Baptist University, Hong Kong. He is now with the Lenovo Machine Intelligence Center, Hong Kong (e-mail:
[email protected]). Kai Cao was with the Department of Computer Science and Engineering, Michigan State University, East Lansing, MI 48824 USA (e-mail:
[email protected]). Xiangyuan Lan and Pong C. Yuen are with the Department of Computer Science, Hong Kong Baptist University, Hong Kong (e-mail: xiangyuanlan@ life.hkbu.edu.hk;
[email protected]). Digital Object Identifier 10.1109/TIFS.2020.3009590 1https://www.apple.com/iphone-x/#face-id 2http://fortune.com/2016/09/12/border-security-biometrics/ 3http://www.citibank.com.hk/english/ways-to-bank/voice-biometrics.htm 4https://www.kairos.com/human-analytics/healthcare Fig. 1. Security and privacy issues introduced by inverting biometric templates. Raw biometric data (e.g., face and fingerprint images) can be reconstructed from the corresponding templates stored in the system. The reconstructed data can then be presented to authentication systems to get access (security issues) and identified by a biometric search engine (privacy issues). Publisher Copyright: {\textcopyright} 2005-2012 IEEE.",
year = "2021",
month = jan,
doi = "10.1109/TIFS.2020.3009590",
language = "English",
volume = "16",
pages = "262--277",
journal = "IEEE Transactions on Information Forensics and Security",
issn = "1556-6013",
publisher = "IEEE",
}