Privacy-preserving multimodal person and object identification

ABSTRACT

In this paper we investigate multimodal biometric person and object identification. We model this process of multimodal identification as multimodal multiple hypothesis testing with independent modalities. We analyze theoretical performance limits that can be attained in such a multimodal protocol in terms of exponents of average error probability. Furthermore, we address a privacy related issues in this paper. In particular, we consider performance/privacy trade-off due to the indirect multimodal identification performed in a secret subspace and approximate the obtained performance limits using properties of random projections. Finally, a set of experiments exemplifies our findings.

REFERENCES

• 1: A. K. Jain, A. Ross, and S. Pankanti, "Biometrics: A tool for information security," IEEE Trans. on Information Forensics and Security, vol. 1, no. 2, pp. 125--143, June 2006.
• 2: Matteo Golfarelli , Dario Maio , Davide Maltoni, On the Error-Reject Trade-Off in Biometric Verification Systems, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.19 n.7, p.786-796, July 1997 [doi>10.1109/34.598237]
• 3: Anil K. Jain , David Maltoni, Handbook of Fingerprint Recognition, Springer-Verlag New York, Inc., Secaucus, NJ, 2003
• 4: A. K. Jain, S. C. Dass, and K. Nandakumar, "Can soft biometric traits assist user recognition?" in First international conference on Biometric Authentication, 2004, pp. 561--572.
• 5: L. Hong, A. K. Jain, and S. Pankanti, "Can multibiometrics improve performance?" Department of Computer Science, Michigan State University, East Lansing, Michigan, Tech. Rep. MSU-CSE-99-39, December 1999.
• 6: Lin Hong , Anil K. Jain, Integrating Faces and Fingerprints for Personal Identification, Proceedings of the Third Asian Conference on Computer Vision-Volume I, p.16-23, January 08-10, 1998
• 7: Arun A. Ross , Karthik Nandakumar , Anil K. Jain, Handbook of Multibiometrics (International Series on Biometrics), Springer-Verlag New York, Inc., Secaucus, NJ, 2006
• 8: Thomas M. Cover , Joy A. Thomas, Elements of information theory, Wiley-Interscience, New York, NY, 1991
• 9: A. Ross, R. G. Hong, A. K. Jain, and S. Pankanti, Feature level fusion using hand and face biometrics, in SPIE Conf. Biometric Technology for Human Identification II, 2005, pp. 196--204.
• 10: O. Koval, S. Voloshynovskiy, and T. Pun, "Error exponent analysis of person identification based on fusion of independent modalities," in Proceedings of the SPIE International Conference on Security and Watermarking of Multimedia Contents III, San Jose, CA, USA, January 2007.
• 11: B. Ulery, W. Fellner, A. H. P. Hallinan and, C. Watson, "Evaluation of selected biometric fusion techniques," Tech. Rep., http://www.itl.nist.gov/iad/894.03/pact/ir7346 C.pdf.
• 12: Roberto Brunelli , Daniele Falavigna, Person Identification Using Multiple Cues, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.17 n.10, p.955-966, October 1995 [doi>10.1109/34.464560]
• 13: E. S. Bigün , Josef Bigün , Benoît Duc , S. Fischer, Expert Conciliation for Multi Modal Person Authentication Systems by Bayesian Statistics, Proceedings of the First International Conference on Audio- and Video-Based Biometric Person Authentication, p.291-300, March 12-14, 1997
• 14: O. Ushmaev and S. Novikov, "Biometric fusion: Robust approach," in Workshop on Multimodal User Authent. (MMUA 2006), Toulouse, France, 2006.
• 15: E. Martinian, S. Yekhanin, and J. Yedidia, "Secure biometrics via syndromes," in 43rd Annual Allerton Conference on Communications, Control, and Computing, Monticello, IL, USA, October 2005.
• 16: U. Maurer, "Secret key agreement by public discussion from common information," IEEE Trans. Inform. Theory, vol. 39, pp. 733--742, 1993.
• 17: R. Ahlswede and I. Csiszar, "Common randomness in information theory and cryptography -- part i: secret sharing," IEEE Trans. Inform. Theory, vol. 39, no. 4, pp. 1121--1132, 1993.
• 18: D. Slepian and J. Wolf, "Noiseless encoding of correlated information sourcea," IEEE Trans. Information Theory, vol. 19, pp. 471--480, July 1973.
• 19: O. Koval, S. Voloshynovskiy, and T. Pun, Privacy-preserving biometric person identification," in EUSIPCO'08, Lausanne, Switzerland, August 2008.
• 20: Pim Tuyls , Boris Skoric , Tom Kevenaar, Security with Noisy Data: Private Biometrics, Secure Key Storage and Anti-Counterfeiting, Springer-Verlag New York, Inc., Secaucus, NJ, 2007
• 21: O. Koval, S. Voloshinovskiy, and T. Pun, Privacy-preserving biometric person identification, Proc. 2008 European Signal Processing Conference (EUSIPCO-2008), Augusst 2008, Lausanne, Switzerland.
• 22: Umut Uludag , Anil K. Jain, Secure biometric systems, Michigan State University, East Lansing, MI, 2006
• 23: M. R. Freire, J. Fierrez, J. Galbally, andJ. Ortega-Garcia, "Biometric hashing based on genetic selection and its application to on-line signatures",Proc. IAPR International Conference on Biometrics, ICB, August,2007.
• 24: Arun Abraham Ross , Anil K. Jain, Information fusion in fingerprint authentication, Michigan State University, East Lansing, MI, 2003
• 25: O. Koval, S. Voloshynovskiy, and T. Pun, "Analysis of multimodal binary detection systems based on dependent/independent modalities," in IEEE Int Workshop on Multimedia Sign. Proc. (MMSP'07), Chania, Crete, Greece, October 2007.
• 26: H. van Trees, Detection, Estimation, and Modulation Theory, Part I. New York, Wiley, 1968.
• 27: C.C. Leang and D.H.Johnson, "On the asymptotics of m-hypothesis bayesian detection," IEEE Trans. on Information Theory, vol. 43, no. 1, pp. 280--282, January 1997.
• 28: W. B. Johnson and J. Lindenstrauss, "Extensions of lipschitz mapping into hilbert space," Contemporary Mathematics, no. 26, pp. 189--206, 1984.
• 29: N. Al-Dhahir and J. M. Cioffi, "Optimum finite-length equalization for multicarrier transceivers," IEEE Trans. on Inf. Com., vol. 44, no. 1, pp. 56--63, Jan. 1998.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.m MISCELLANEOUS

General Terms:
Performance

Keywords:
dimensionality reduction, hypothesis testing, multimodal signal processing, object identification, privacy, random projections