(Voice-) biometric data is considered as personally identifiable information, that is, the increasing demand on (mobile) speaker recognition systems calls for applications which prevent from privacy threats, such as identity-theft or tracking without consent. Technologies of biometric template protection, in particular biometric cryptosystems, fulfil standardised properties of irreversibility and unlinkability which represent appropriate countermeasures to such vulnerabilities of conventional biometric recognition systems. Thereby, public confidence in and social acceptance of biometric applications is strengthened. In this work the authors propose a binarisation technique, which is used to extract scalable high-entropy binary voice reference data (templates) from speaker models, based on Gaussian mixture models and universal background models. Binary feature vectors are then protected within a template protection scheme in particular, fuzzy commitment scheme, in which error correction list-decoding is employed to overcome high intra-class variance of voice samples. In experiments, which are evaluated out on a text-independent speaker corpus of 339 individuals, it is demonstrated that the fully ISO/IEC IS 24745 compliant system achieves privacy protection at a negligible loss of biometric performance, confirming the soundness of the presented approach.

References

1. 1)
  - 25. Johnson, R.C., Scheirer, W.J., Boult, T.E.: ‘Secure voice based authentication for mobile devices: Vaulted voice verification’, CoRR, 2012, abs/1212.0042.
2. 2)
  - C. Roberts . Biometric attack vectors and defences. Comput. Secur. , 14 - 25
3. 3)
  - 13. Monrose, F., Reiter, M.K., Li, Q., Wetzel, S.: ‘Using voice to generate cryptographic keys’. Proc. Speaker Odyssey 2001, The Speech Recognition Workshop, 2001, pp. 237–242.
4. 4)
  - 20. Inthavisas, K., Lopresti, D.: ‘Speech cryptographic key regeneration based on password’. Proc. 2011 Int. Joint Conf. on Biometrics, ser. IJCB'11, IEEE, 2011, pp. 1–7.
5. 5)
  - J.P. Campbell . Speaker recognition: a tutorial. Proc. IEEE , 1437 - 1462
6. 6)
  - N.K. Ratha , J.H. Connell , R.M. Bolle . Enhancing security and privacy in biometric-based authentication systems. IBM Syst. J. , 3 , 614 - 634
7. 7)
  - T. Kinnunen , H. Li . An overview of text-independent speaker recognition: from features to supervectors. Speech Commun. , 1 , 12 - 40
8. 8)
  - 17. Teoh, A., Yuang, C.T.: ‘Cancelable biometrics realization with multispace random projections’, IEEE Trans. Syst. Man Cybern. B: Cybern., 2007, 37, (5), pp. 1096–1106 (doi: 10.1109/TSMCB.2007.903538).
9. 9)
  - 26. Argones Rua, E., Maiorana, E., Alba Castro, J., Campisi, P.: ‘Biometric template protection using universal background models: An application to online signature’, IEEE Trans. Inf. Forensics Sec., 2012, 7, (1), pp. 269–282 (doi: 10.1109/TIFS.2011.2168213).
10. 10)
  - 23. Johnson, R., Boult, T.: ‘With vaulted voice verification my voice is my key’. Int. Conf. on Technologies for Homeland Security (HST'13), November 2013, pp. 453–459.
11. 11)
  - 27. Pelecanos, J., Sridharan, S.: ‘Feature warping for robust speaker verification’.
12. 12)
  - 35. Rathgeb, C., Uhl, A.: ‘Adaptive fuzzy commitment scheme based on iris-code error analysis’. Second European Workshop on Visual Information Processing (EUVIP'10), 2010, pp. 41–44.
13. 13)
  - 12. Monrose, F., Reiter, M.K., Li, Q., Wetzel, S.: ‘Cryptographic key generation from voice’. Proc. IEEE Symp. on Security and Privacy, IEEE, 2001, pp. 202–213.
14. 14)
  - 5. Inthavisas, K., Lopresti, D.: ‘Attacks on speech biometric authentication’. Proc. of Int. Conf. on Image Processing, Computer Vision, and Pattern Recognition (IPCV 2011), 2011, pp. 310–316.
15. 15)
  - 7. Rathgeb, C., Uhl, A.: ‘A survey on biometric cryptosystems and cancelable biometrics’, EURASIP J. Inf. Secur., 2011, 2011, (3) pp. 1–25.
16. 16)
  - J.G. Daugman . The importance of being random: statistical principles of iris recognition. Pattern Recognit. , 279 - 291
17. 17)
  - 24. Juels, A., Sudan, M.: ‘A fuzzy vault scheme’. Proc. IEEE Int. Symp. on Information Theory, 2002, p. 408.
18. 18)
  - 29. Elias, P.: ‘Error-correcting codes for list decoding’, IEEE Trans. Inf. Theory, 1991, 37, (1), pp. 5–12 (doi: 10.1109/18.61123).
19. 19)
  - 28. Rathgeb, C., Uhl, A.: ‘Statistical attack against fuzzy commitment scheme’, IET Biometrics, 2012, 1, (2), pp. 94–104 (doi: 10.1049/iet-bmt.2011.0001).
20. 20)
  - 37. Simoens, K., Yang, B., Zhou, X., Beato, F., Busch, C., Newton, E., Preneel, B.: ‘Criteria towards metrics for benchmarking template protection algorithms’. Fifth IAPR Int. Conf. on Biometrics (ICB), 2012, pp. 498–505.
21. 21)
  - T. Ignatenko , F.M.J. Willems . Information leakage in fuzzy commitment schemes. Trans. Inf. Forensics Sec. , 2 , 337 - 348
22. 22)
  - 8. ISO/IEC JTC1 SC27 Security Techniques: ISO/IEC 24745:2011. Information Technology–Security Techniques–Biometric Information Protection, International Organization for Standardization, 2011.
23. 23)
  - 22. Juels, A., Wattenberg, M.: ‘A fuzzy commitment scheme’. Proc. Sixth ACM Conf. on Computer and Communications Security, ACM, 1999, pp. 28–36.
24. 24)
  - J. Bringer , H. Chabanne , G. Cohen , B. Kindarji , G. Zémor . Theoretical and practical boundaries of binary secure sketches. IEEE Trans. Inf. Forensics Sec. , 673 - 683
25. 25)
  - 21. Inthavisas, K., Lopresti, D.: ‘Secure speech biometric templates for user authentication’, Biometrics, IET, 2012, 1, (1), pp. 46–54 (doi: 10.1049/iet-bmt.2011.0008).
26. 26)
  - U. Uludag , S. Pankanti , S. Prabhakar , A. Jain . Biometric cryptosystems: issues and challenges. Proc. IEEE , 6 , 948 - 960
27. 27)
  - 40. ISO/IEC TC JTC1 SC37 Biometrics: ‘ISO/IEC 19795-1:2006. Information Technology – Biometric Performance Testing and Reporting – Part 1: Principles and Framework’. Int. Organization for Standardization and Int. Electrotechnical Committee, March 2006.
28. 28)
  - A. Shamir . How to share a secret. Commun. ACM , 11 , 612 - 613
29. 29)
  - A.K. Jain , K. Nandakumar , A. Nagar . Biometric template security. EURASIP J. Adv. Signal Process , 1 - 17
30. 30)
  - 11. Monrose, F., Reiter, M.K., Wetzel, S.: ‘Password hardening based on keystroke dynamics’. Proc. Sixth ACM Conf. on Computer and Communications Security, ACM, 1999, pp. 73–82.
31. 31)
  - A. Jain , A. Ross , S. Prabhakar . An introduction to biometric recognition. IEEE Trans. Circuits Syst. Video Technol. , 1 , 4 - 20
32. 32)
  - F. Hao , R. Anderson , J. Daugman . Combining cryptography with biometrics effectively. IEEE Trans. Comput. , 9 , 1081 - 1088
33. 33)
  - 31. Viveros, R., Balasubramanian, K., Balakrishnan, N.: ‘Binomial and negative binomial analogues under correlated bernoulli trials’, Am. Stat., 1984, 48, (3), pp. 243–247.
34. 34)
  - A.B.J. Teoh , L. Chong . Secure speech template protection in speaker verification system. Speech Commun. , 2 , 150 - 163
35. 35)
  - E.J.C. Kelkboom , J. Breebaart , T.A.M. Kevenaar , I. Buhan , R.N.J. Veldhuis . Preventing the decodability attack based cross-matching in a fuzzy commitment scheme. Trans. Inf. Forensics Sec. , 1 , 107 - 121
36. 36)
  - 15. Atah, J.A., Howells, G.: ‘Key generation in a voice based template free biometric security system’. Proc. of the 2009 Joint COST 2101 and 2102 Int. Conf. on Biometric ID Management and Multimodal Communication, Springer-Verlag, 2009, pp. 170–177.
37. 37)
  - 18. Rathgeb, C., Uhl, A.: ‘Two-factor authentication or how to potentially counterfeit experimental results in biometric systems’. Proc. of the Seventh Int. Conf. on Image Analysis and Recognition–Volume Part II, ser. ICIAR'10, Springer-Verlag, 2010, pp. 296–305.
38. 38)
  - 28. You, C., Li, H., Ma, B., Lee, K.-A.: ‘Effect of relevance factor of maximum a posteriori adaptation for gmm-svm in speaker and language recognition’. Proc. of INTERSPEECH. ISCA, 2012.
39. 39)
  - 32. Stoianov, A., Kevenaar, T., van der Veen, M.: ‘Security issues of biometric encryption’. 2009 IEEE Toronto Int. Conf. on Science and Technology for Humanity (TIC-STH), 2009, pp. 34–39.
40. 40)
  - 19. Adler, A.: ‘Vulnerabilities in biometric encryption systems’. Audio- and Video-Based Biometric Person Authentication, ser. LNCS, Springer, 2005, vol. 3546, pp. 1100–1109.

Biometric template protection for speaker recognition based on universal background models

References

Related content