Abstract Nowadays, biometric recognition has been widely applied in various aspects of security applications because of its safety and convenience. However, unlike passwords or tokens, biometric features are naturally noisy and cannot be revoked once they are compromised. Overcoming these two weaknesses is an essential and principal demand. With a hybrid approach, we propose a scheme that combines the Artificial Neural Network (ANN) and the Secure Sketch concept to generate strong keys from a biometric trait while guaranteeing revocability, template protection and noisy tolerance properties. The ANN with high noisy tolerance capacity enhances the recognition by learning the distinct features of a person, assures the revocable and non-invertible properties for the transformed template. The error correction ability of a Secure Sketch concept’s construction significantly reduces the false rejection rate for the enroller. To assess the scheme’s security, the average remaining entropy is measured on the generated keys. Empirical experiments with standard datasets demonstrate that our scheme is able to achieve a good trade-off between the security and the recognition performance when being applied with the face biometrics.

References

[1] Almaadeed N., Aggoun A., and Amira A., Speaker Identification Using Multimodal Neural Networks and Wavelet Analysis, IET Biometrics, vol. 4, no. 1, pp. 18-28, 2015.

[2] Arunachalam M. and Subramanian K., AES Based Multimodal Biometric Authentication using Cryptographic Level Fusion with Fingerprint and Finger Knuckle Print, The International Arab Journal of Information Technology, vol. 12, no. 5, pp. 431-440, 2015.

[3] Babaie-Zadeh M., Jutten C., and Mohimani H., On the Error of Estimating the Sparsest Solution of Underdetermined Linear Systems, * mn , 0,1 340 The International Arab Journal of Information Technology, Vol. 15, No. 2, March 2018 IEEE Transaction on Information Theory, vol. 57, no. 12, pp. 7840-7855, 2011.

[4] Chafia F., Salim C., and Farid B., A Biometric Crypto-system for Authentication, Machine and Web Intelligence, Algiers, pp. 434-438, 2010.

[5] Chen H. and Chen H., A hybrid Scheme for Securing Fingerprint Templates, International Journal of Information Security, vol. 9, no. 5, pp. 353-361, 2010.

[6] Dodis Y., Ostrovsky R., Reyzin L., and Smith A., Fuzzy Extractors: How to Gener-ate Strong Keys from Biometrics and Other Noisy Data, SIAMJ Journal on Computing, vol. 38, no. 1, pp. 97-139, 2008.

[7] Donoho L., Tsaig Y., Drori I., and Starck J., Sparse Solution of Underdetermined Systems of Linear Equations by Stage wise Orthogonal Matching Pursuit, IEEE Transactions on Information Theory, vol. 58, no. 2, pp. 1094- 1121, 2012.

[8] Han J. and Kamber M., Data Mining: Concepts and Techniques 2nd, Morgan Kaufman, 2006.

[9] Jain K., Nandakumar K., and Nagar A., Biometric Template Security, EURASIP Journal on Advances in Signal Processing, vol. 2008, no. 113, 2008.

[10] Juels A. and Sudan M., A Fuzzy Vault Scheme, Designs, Codes and Cryptography, vol. 38, no. 2, pp. 237-257, 2006.

[11] Juels A. and Wattenberg M., A Fuzzy Commitment Scheme, in Proceedings of the 6th ACM Conference on Computer and Communications Security, New York, pp. 28-36, 1999.

[12] Lai J., On Sparse Solutions of Underdetermined Linear Systems, Journal of Concrete & Applicable Mathematics, vol. 8, no. 1, pp. 296, 2010

[13] Li Q., Sutcu Y., and Memon N., Secure Sketch for Biometric Templates, in Proceedings of the 12th International Conference on Theory and Application of Cryptology and Information Security, Shanghai, pp. 99-113, 2006.

[14] Nagar A., Nandakumar K., and Jain K., Securing Fingerprint Template: Fuzzy Vault with Minutiae Descriptors, in Proceedings of 19th International Conference on Pattern Recognition, Tampa, pp. 1-4, 2008.

[15] Nandakumar K. and Jain K., Biometric Template Protection Schemes: Bridging the Performance Gap Between Theory and Practice, IEEE Signal Processing Magazine, vol. 32, no. 5, pp. 88-100, 2015.

[16] Nandakumar K., Nagar A., and Jain K., Hardening Fingerprint Fuzzy Vault using Password, in Proceedings of Conference on Biometrics, Seoul, pp. 927-937, 2007.

[17] Russell S. and Norvig P., Artificial Intelligence a Modern Approach 1st, Alan Apt, 1995.

[18] Sharma P., Yadav N., and Arya V., Pose- invariant Face Recognition using Curvelet Neural Network, IET Biometrics, vol. 3, no. 3, pp. 128-138, 2014.

[19] Spacek L., Libor Spacek s Faces94 database, http://cswww.essex.ac.uk/mv/allfaces/faces94.ht ml, Last Visited 2014.

[20] Sutcu Y., Li Q., and Memon N., How to Protect Biometric Templates, in Proceedings of SPIE Security, Steganography, and Watermarking of Multimedia Contents, vol. 6505, San jose, 2007.

[21] Turk M. and Pentland A., Eigenfaces for Recognition, Cognitive Neuroscience, vol. 3, no. 1, pp. 71-86, 1991. Tran-Khanh Dang got his PhD degree (Dr.techn.) in May 2003 at FAW Institute, University of Linz (Austria). Afterwards, he had been working as a lecturer and researcher at the School of Computing Science, Middlesex University in London (UK) since August 2003. Currently, he is an associate professor of computer science and a vice-dean at the Faculty of Computer Science and Engineering, HCMUT, Vietnam. Dr. Dang s research interests include database and information security, privacy protection in location based services, mobile data security, and big data management. He is also the founder of the Data SecuriTy Applied Research (D- STAR) Lab (http://www.dstar.edu.vn). He has published more than 140 scientific papers in international journals and conferences. Van-Quoc-Phuong Huynh received his MSc degree in Computer Science from Vietnam National University - Ho Chi Minh City University of Technology (VNU-HCMUT). He is currently a lecturer of Information System department, Computer Science and Engineering faculty, HCMUT. His main research interests include biometrics-based and information security, data mining and privacy preserving data mining. Hai Truong received his MSc degree in Advanced Computing Science from the School of Computer Science of The University of Nottingham, UK. He is currently a lecturer of the Information System department, Computer Sciene and Engineering faculty, HCMUT. His research interests include biometric template security, authentication and recognition, privacy preserving in social networks.