| | This Article | |
| |
| |
| | Share | |
| |
| |
| | Bibliographic References | |
| |
| |
| | Add to: | |
| |
 Digg
 Furl
 Spurl
 Blink
 Simpy
 Google
 Del.icio.us
 Y!MyWeb
| |
| | Search | |
| |
| |
| | |
From Scores to Face Templates: A Model-Based Approach
December 2007 (vol. 29 no. 12)
pp. 2065-2078
Regeneration of templates from match scores has security and privacy implications related to any biometric authentication system. We propose a novel paradigm to reconstruct face templates from match scores using a linear approach. It proceeds by first modeling the behavior of the given face recognition algorithm by an affine transformation. The goal of the modeling is to approximate the distances computed by a face recognition algorithm between two faces by distances between points, representing these faces, in an affine space. Given this space, templates from an independent image set (break-in) are matched only once with the enrolled template of the targeted subject and match scores are recorded. These scores are then used to embed the targeted subject in the approximating affine (non-orthogonal) space. Given the coordinates of the targeted subject in the affine space, the original template of the targeted subject is reconstructed using the inverse of the affine transformation. We demonstrate our ideas using three, fundamentally different, face recognition algorithms: Principal Component Analysis (PCA) with Mahalanobis cosine distance measure, Bayesian intra-extrapersonal classifier (BIC), and a feature-based commercial algorithm. To demonstrate the independence of the break-in set with the gallery set, we select face templates from two different databases: Face Recognition Grand Challenge (FRGC) and Facial Recognition Technology (FERET) Database (FERET). With an operational point set at 1% False Acceptance Rate (FAR) and 99% True Acceptance Rate (TAR) for 1196 enrollments (FERET gallery), we show that at most 600 attempts (score computations) are required to achieve a 73% chance of breaking in as a randomly chosen target subject for the commercial face recognition system. With similar operational set up, we achieve a 72% and 100% chance of breaking in for the Bayesian and PCA based face recognition systems, respectively. With three different levels of score quantization, we achieve 69%, 68% and 49% probability of break-in, indicating the robustness of our proposed scheme to score quantization. We also show that the proposed reconstruction scheme has 47% more probability of breaking in as a randomly chosen target subject for the commercial system as compared to a hill climbing approach with the same number of attempts. Given that the proposed template reconstruction method uses distinct face templates to reconstruct faces, this work exposes a more severe form of vulnerability than a hill climbing kind of attack where incrementally different versions of the same face are used. Also, the ability of the proposed approach to reconstruct actual face templates of the users increases privacy concerns in biometric systems.
[1] S. Prabhakar, S. Pankanti, and A. Jain, “Biometric Recognition: Security and Privacy Concerns,” IEEE Security and Privacy Magazine, vol. 1, no. 2, pp. 33-42, Apr. 2003.
[2] T. Matsumoto, H. Matsumoto, K. Yamada, and S. Hoshino, “Impact of Artificial Gummy Fingers on Fingerprint Systems,” Proc. SPIE, Optical Security and Counterfeit Deterrence Techniques IV, vol. 4667, pp. 275-289, 2002.
[3] A.K. Jain and S. Li, Handbook of Face Recognition. Springer, 2005.
[4] G. Hachez, F. Koeune, and J. Quisquater, “Biometrics, Access Control, Smart Cards: A Not So Simple Combination,” Proc. Fourth Smart Card Research and Advanced Applications Conf., vol. 4, pp. 273-288, Sept. 2000.
[5] S. Schimke, C. Vielhauer, and T. Kalker, “Security Analysis for Biometric Data in ID Documents,” Proc. SPIE-IS&T Symp. Electronic Imaging, vol. 5681, pp. 474-485, 2005.
[6] C. Soutar, D. Roberge, S.A. Stojanov, R. Gilroy, and B.V.K. Vijaya, “Biometric Encryption Using Image Processing,” Proc. SPIE, Optical Security and Counterfeit Deterrence Techniques II, vol. 3314, pp. 178-188, 1998.
[7] U. Uludag, S. Pankanti, S. Prabhakar, and A.K. Jain, “Biometric Cryptosystems: Issues and Challenges,” Proc. IEEE, special issue on enabling security technologies for digital rights management, vol. 92, no. 6, pp. 948-960, June 2004.
[8] N. Ratha, J. Connell, and R. Bolle, “An Analysis of Minutiae Matching Strength,” Proc. Int'l Conf. Audio and Video-Based Biometric Person Authentication, 2001.
[9] BioAPI, BioAPI 2.0—International Version, BioAPI Consortium, http://www.bioapi.orginternationalversion.html , 2005.
[10] R. Bolle, J.H. Connell, S. Pankanti, N.K. Ratha, and A.W. Senior, Guide to Biometrics. Springer, 2004.
[11] S. Nanavati, M. Thieme, and R. Nanavati, Biometrics: Identity Verification in a Networked World. John Wiley & Sons, 2005.
[12] P. Phillips, H. Wechsler, J. Huang, and P.J. Rauss, “The FERET Database and Evaluation Procedure for Face Recognition Algorithms,” Image and Vision Computing, vol. 16, pp. 295-306, 1998.
[13] P.J. Phillips, P. Flynn, T. Scruggs, K. Bowyer, J. Chang, K. Hoffman, J. Marques, J. Min, and W. Worek, “Overview of the Face Recognition Grand Challenge,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 947-954, June 2005.
[14] M.A. Turk and P. Pentland, “Face Recognition Using Eigenfaces,” Proc. IEEE Conf. Conf. Computer Vision and Pattern Recognition, pp.586-591, June 1991.
[15] B. Moghaddam and A. Pentland, “Beyond Eigenfaces: Probabilistic Matching for Face Recognition,” Proc. Int'l Conf. Automatic Face and Gesture Recognition, pp. 30-35, 1998.
[16] C. Soutar, “Biometric System Security,” Secure, vol. 5, pp. 46-49, 2002.
[17] A. Adler, “Images Can Be Regenerated from Quantized Biometric Match Score Data,” Proc. Canadian Conf. Electrical and Computer Eng., pp. 469-472, May 2004.
[18] U. Uludag and A. Jain, “Attacks on Biometric Systems: A Case Study in Fingerprints,” Proc. SPIE-EI 2004, Security, Steganography and Watermarking of Multimedia Contents, pp. 622-633, Jan. 2004.
[19] A. Adler, “Vulnerabilities in Biometric Encryption System,” Proc. Int'l Conf. Audio and Video-Based Biometric Person Authentication, pp. 1100-1109, July 2005.
[20] D. Lopresti and J. Raim, “The Effectiveness of Generative Attacks on an Online Handwriting Biometric,” Proc. Int'l Conf. Audio and Video-Based Biometric Person Authentication, pp. 1090-1099, July 2005.
[21] P. Belhumeur, J. Hespanha, and D. Kriegman, “Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 711-720, July 1997.
[22] P. Comon, “Independent Component Analysis, a New Concept?” Signal Processing, vol. 36, no. 3, Apr. 1994.
[23] L. Wiskott, J. Fellous, N. Kruger, and C. Malsburg, “Face Recognition by Elastic Bunch Graph Matching,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 1160-1169, July 1997.
[24] X. Liu, A. Srivastava, and K. Gallivan, “Optimal Linear Representations of Images for Object Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 5, pp. 662-666, May 2004.
[25] P. Mohanty, S. Sarkar, and R. Kasturi, “Designing Affine Transformations Based Face Recognition Algorithms,” Proc. IEEE Workshop Face Recognition Grand Challenge, June 2005.
[26] E. Pekalska, P. Paclik, and R. Duin, “A Generalized Kernel Approach to Dissimilarity-Based Classification,” J. Machine Learning Research, vol. 2, no. 2, pp. 175-211, 2002.
[27] J. Tenenbaum, V. Silva, and J. Langford, “A Global Geometric Framework for Nonlinear Dimensionality Reduction,” Science Magazine, vol. 290, no. 5500, 2000.
[28] S. Roweis and L. Saul, “Nonlinear Dimensionality Reduction by Locally Linear Embedding,” Science Magazine, vol. 290, no. 5500, 2000.
[29] T. Cox and M. Cox, Multidimensional Scaling, second ed. Chapman and Hall, 1994.
[30] I. Borg and P. Groenen, “Modern Multidimensional Scaling,” Springer Series in Statistics, Springer, 1997.
[31] J. Gower and P. Legendree, “Metric and Euclidean Properties of Dissimilarity Coefficients,” J. Classification, vol. 3, pp. 5-48, 1986.
[32] V. Roth, J. Laub, M. Kawanabe, and J.M. Buhmann, “Optimal Cluster Preserving Embedding of Nonmetric Proximity Data,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 12, pp. 1540-1551, Dec. 2003.
[33] R. Beveridge, D. Bolme, M. Teixeira, and B. Draper, “The CSU Face Identification Evaluation System,” Machine Vision and Applications, vol. 16, no. 2, pp. 128-138, 2005.
[34] D. Bolme, “The Bayesian Intrapersonal/Extrapersonal Classifiers,” master's thesis, Colorado State Univ., Computer Science Dept., July 2003.
[35] N. Ratha, J. Connell, and R. Bolle, “Enhancing Security and Privacy in Biometrics-Based Authentication Systems,” IBM Systems J., vol. 40, no. 3, 2001.
[36] T. Boult, “Robust Distance Measures for Face-Recognition Supporting Revocable Biometric Tokens,” Proc. Int'l Conf. Automatic Face and Gesture Recognition, pp. 560-566, 2006.
Index Terms:
Face template reconstruction, probability of break-in, multidimensional scaling, security and privacy issues in biometric systems., hill climbing attack
Citation:
Pranab Mohanty, Sudeep Sarkar, Rangachar Kasturi, "From Scores to Face Templates: A Model-Based Approach," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 12, pp. 2065-2078, June 2007, doi:10.1109/TPAMI.2007.1129
