Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Face template protection using deep LDPC codes learning

  • Author(s): Lingying Chen 1, 2 ; Guanghui Zhao 1 ; Junwei Zhou 1 ; Anthony T.S. Ho 1, 3 ; Lee-Ming Cheng 4
    • View affiliations
  • Source: Volume 8, Issue 3, May 2019, p. 190 – 197
    DOI:  10.1049/iet-bmt.2018.5156 , Print ISSN 2047-4938, Online ISSN 2047-4946
© The Institution of Engineering and Technology
Received 13/07/2018, Accepted 08/11/2018, Revised 20/10/2018, Published 15/11/2018

There is a noticeable tendency to apply deep convolutional neural network (CNN) in facial identification, since it is able to boost performance in face recognition and verification. However, due to the users have unique facial, exposure of face template to adversaries can severely compromise system security and users’ privacy. Here, the authors propose a face template protection technique by using multi-label learning, which maps the facials into low-density parity-check (LDPC) codes. Firstly, a random binary sequence is generated to represent a user and further hashed to produce the protected template. During the training, the random binary sequences are encoded by an LDPC encoder to produce diverse binary codes. Based on carefully designed deep multi-label learning, the facial features of each user are mapped to a diverse binary code. In the process of recognition and verification, the deep CNN mapping architecture is modelled as a Gaussian channel, while the noise brought by intra-variations in the outputs of CNN can be removed by the LDPC decoder. Thus, a robust face template protection scheme is achieved. The simulation results on PIE and extended Yale B indicate that the proposed scheme achieves high genuine accept rate at 1% false accept rate.

Inspec keywords: face recognition; parity check codes; learning (artificial intelligence); neural nets; biometrics (access control); binary codes

Other keywords: deep convolutional neural network; deep CNN mapping architecture; face template protection technique; diverse binary code; protected template; deep LDPC codes; low-density parity-check codes; noticeable tendency; system security; robust face template protection scheme; verification; random binary sequence; LDPC encoder; carefully designed deep multilabel learning; facial identification; facial features; face recognition; LDPC decoder

Subjects: Neural computing techniques; Data security; Image recognition; Knowledge engineering techniques; Computer vision and image processing techniques

References

    1. 1)
      • 2. Samangouei, P., Chellappa, R.: ‘Convolutional neural networks for attribute-based active authentication on mobile devices’. IEEE Int. Conf. on Biometrics Theory, Applications and Systems, Niagara Falls, NY, 2016, pp. 1–8.
    2. 2)
      • 29. Savvides, M., Kumar, B.V.K.V., Khosla, P.K.: ‘Cancelable biometric filters for face recognition’. Int. Conf. on Pattern Recognition, Cambridge, UK, 2004, pp. 922–925.
    3. 3)
      • 4. Mohammadi, A., Bhattacharjee, S., Marcel, S.: ‘Deeply vulnerable: a study of the robustness of face recognition to presentation attacks’, IET Biometrics, 2018, 7, (1), pp. 15–26.
    4. 4)
      • 26. Pandey, R.K., Zhou, Y., Kota, B.U., et al: ‘Deep secure encoding for face template protection’. IEEE Conf. on Computer Vision and Pattern Recognition Workshops, Las Vegas, Nevada, 2016, pp. 77–83.
    5. 5)
      • 46. MacKay, D.J., Neal, R.M.: ‘Near Shannon limit performance of low density parity check codes’, Electron. Lett., 1996, 32, (18), pp. 1645–1648.
    6. 6)
      • 31. Sandhya, M., Prasad, M.V.N.K.: ‘Cancelable fingerprint cryptosystem using multiple spiral curves and fuzzy commitment scheme’, Int. J. Pattern Recognit. Artif. Intell., 2016, 31, (4), pp. 2555–2564.
    7. 7)
      • 30. Sutcu, Y., Sencar, H.T., Memon, N.: ‘A secure biometric authentication scheme based on robust hashing’. Workshop on Multimedia and Security, New York, USA, 2005, pp. 111–116.
    8. 8)
      • 44. Jia, Y., Shelhamer, E., Donahue, J., et al: ‘Caffe: convolutional architecture for fast feature embedding’. ACM Int. Conf. on Multimedia, Orlando, Florida, 2014, pp. 675–678.
    9. 9)
      • 6. Saranya, R., Prabhu, S.: ‘Image encryption using RSA algorithm with biometric recognition’, Int. J. Adv. Trends Comput. Sci. Eng., 2016, 5, (11), pp. 19149–19154.
    10. 10)
      • 1. Lau, J.K.Y., Kaheel, A., El-Saban, M., et al: ‘Using facial data for device authentication or subject identification’.US Patent, 9,652,663, 2017.
    11. 11)
      • 13. Sutcu, Y., Li, Q., Memon, N.: ‘Secure sketches for protecting biometric templates’, Campisi, P. (ED.): Secure Biometrics, (Springer, Verlag London, 2013), pp. 69–104, DOI https://doi.org/10.1007/978-1-4471-5230-9.
    12. 12)
      • 3. Samangouei, P., Patel, V.M., Chellappa, R.: ‘Facial attributes for active authentication on mobile devices’, Image Vis. Comput., 2016, 58, pp. 181–192.
    13. 13)
      • 48. MacKay, D.J.: ‘Good error-correcting codes based on very sparse matrices’, IEEE Trans. Inf. Theory, 1999, 45, (2), pp. 399–431.
    14. 14)
      • 20. Qin, C., Chen, X., Ye, D., et al: ‘A novel image hashing scheme with perceptual robustness using block truncation coding’, Inf. Sci., 2016, 361–362, pp. 84–99.
    15. 15)
      • 45. Gallager, R.: ‘Low-density parity-check codes’, IRE Trans. Inf. Theory, 1962, 8, (1), pp. 21–28.
    16. 16)
      • 17. Kaur, H., Khanna, P.: ‘Biometric template protection using cancelable biometrics and visual cryptography techniques’, Multimedia Tools Appl., 2016, 75, (23), pp. 16333–16361.
    17. 17)
      • 41. Kschischang, F.R., Frey, B.J., Loeliger, H.A.: ‘Factor graphs and the sum-product algorithm’, IEEE Trans. Inf. Theory, 2001, 47, (2), pp. 498–519.
    18. 18)
      • 56. Farooq, F., Bolle, R.M., Jea, T.Y., et al: ‘Anonymous and revocable fingerprint recognition’. IEEE Conf. on Computer Vision and Pattern Recognition, Minneapolis, Minnesota, 2007, pp. 1–7.
    19. 19)
      • 11. Jegede, A., Udzir, N., Abdullah, A., et al: ‘Revocable and non-invertible multibiometric template protection based on matrix transformation’, Pertanika J. Sci. Technol., 2018, 26, (1), pp. 133–160.
    20. 20)
      • 24. Amos, B., Ludwiczuk, B., Satyanarayanan, M.: ‘OpenFace: a general-purpose face recognition library with mobile applications’. CMU School of Computer Science, 2016, pp. 1–18.
    21. 21)
      • 38. Vizilter, Y., Gorbatcevich, V., Vorotnikov, A., et al: ‘Real-time face identication via cnn and boosted hashing forest’. IEEE Conference on Computer Vision and Pattern Recognition Workshops, Las Vegas, Nevada, 2016, pp. 146–154.
    22. 22)
      • 55. Lai, L., Ho, S.W., Poor, H.V.: ‘Privacy-security trade-offs in biometric security systems’, IEEE Trans. Inf. Forensics Sec., 2011, 6, (1), pp. 122–151.
    23. 23)
      • 28. Gomez-Barrero, M., Galbally, J., Rathgeb, C., et al: ‘General framework to evaluate unlinkability in biometric template protection systems’, IEEE Trans. Inf. Forensics Sec., 2018, 13, (6), pp. 1406–1420.
    24. 24)
      • 7. Nandakumar, K., Jain, A.K.: ‘Biometric template protection: bridging the performance gap between theory and practice’, IEEE Signal Process. Mag., 2015, 32, (5), pp. 88–100.
    25. 25)
      • 18. Sandhya, M., Prasad, M.V.N.K.: ‘Securing fingerprint templates using fused structures’, IET Biometrics, 2017, 6, (3), pp. 173–182.
    26. 26)
      • 10. Khan, S.H., Akbar, M.A., Shahzad, F., et al: ‘Secure biometric template generation for multi-factor authentication’, Pattern Recognit., 2015, 48, (2), pp. 458–472.
    27. 27)
      • 37. Do, T.T., Doan, A.D., Cheung, N.M.: ‘Learning to hash with binary deep neural network’. European Conf. on Computer Vision, Amsterdam, The Netherlands, 2016, pp. 219–234.
    28. 28)
      • 43. Zhang, M.L., Zhou, Z.H.: ‘A review on multi-label learning algorithms’, IEEE Trans. Knowl. Data Eng., 2014, 26, (8), pp. 1819–1837.
    29. 29)
      • 12. Zhang, M., Zhang, J.S., Tan, W.R.: ‘A secure sketch-based authentication scheme for telecare medicine information systems’, J. Inf. Sci. Eng., 2016, 32, pp. 389–402.
    30. 30)
      • 53. Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.: ‘From few to many: illumination cone models for face recognition under variable lighting and pose’, IEEE Trans. Pattern Anal. Mach. Intell., 2001, 23, (6), pp. 643–660.
    31. 31)
      • 50. Bayat-Sarmadi, S., Mozaffari-Kermani, M., Reyhani-Masoleh, A.: ‘Efficient and concurrent reliable realization of the secure cryptographic SHA-3 algorithm’, IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst., 2014, 33, (7), pp. 1105–1109.
    32. 32)
      • 33. Dang, T.K., Truong, Q.C., Le, T.T.B., et al: ‘Cancellable fuzzy vault with periodic transformation for biometric template protection’, IET Biometrics, 2016, 5, (3), pp. 229–235.
    33. 33)
      • 40. Ozel, O., Ulukus, S.: ‘Achieving AWGN capacity under stochastic energy harvesting’, IEEE Trans. Inf. Theory, 2012, 58, (10), pp. 6471–6483.
    34. 34)
      • 22. Sun, Y., Wang, X., Tang, X.: ‘Deep learning face representation from predicting 10,000 classes’. IEEE Conf. on Computer Vision and Pattern Recognition, Columbus, Ohio, 2014, pp. 1891–1898.
    35. 35)
      • 54. Feng, Y.C., Yuen, P.C., Jain, A.K.: ‘A hybrid approach for generating secure and discriminating face template’, IEEE Trans. Inf. Forensics Sec., 2010, 5, (1), pp. 103–117.
    36. 36)
      • 51. Sim, T., Baker, S., Bsat, M.: ‘The CMU pose, illumination, and expression (PIE) database’. IEEE Int. Conf. on Automatic Face and Gesture Recognition, Washington, DC, 2002, pp. 53–58.
    37. 37)
      • 52. Feng, Y.C., Yuen, P.C.: ‘Binary discriminant analysis for generating binary face template’, IEEE Trans. Inf. Forensics Sec., 2012, 7, (2), pp. 613–624.
    38. 38)
      • 27. Kelkboom, E.J.C., Breebaart, J., Kevenaar, T.A.M., et al: ‘Preventing the decodability attack based cross-matching in a fuzzy commitment scheme’, IEEE Trans. Inf. Forensics Sec., 2011, 6, (1), pp. 107–121.
    39. 39)
      • 5. Alahmadi, A., Abdelhakim, M., Ren, J., et al: ‘Defense against primary user emulation attacks in cognitive radio networks using advanced encryption standard’, IEEE Trans. Inf. Forensics Sec., 2014, 9, (5), pp. 772–781.
    40. 40)
      • 19. Gao, Q., Zhang, C.: ‘Constructing cancellable template with synthetic minutiae’, IET Biometrics, 2017, 6, (6), pp. 448–456.
    41. 41)
      • 15. Belguechi, R., Cherrier, E., Rosenberger, C., et al: ‘Operational bio-hash to preserve privacy of fingerprint minutiae templates’, IET Biometrics, 2013, 2, (2), pp. 76–84.
    42. 42)
      • 34. Panwar, A., Singla, P., Kaur, M.: ‘Techniques for enhancing the security of fuzzy vault: a review’, Int. Comput. Tech., Theory Pract. Appl., 2018, 719, pp. 205–213.
    43. 43)
      • 42. Tan, X., Triggs, B.: ‘Enhanced local texture feature sets for face recognition under difficult lighting conditions’, IEEE Trans. Image Process., 2010, 19, (6), pp. 1635–1650.
    44. 44)
      • 23. Schroff, F., Kalenichenko, D., Philbin, J.: ‘FaceNet: a unified embedding for face recognition and clustering’. IEEE Conf. on Computer Vision and Pattern Recognition, Boston, Massachusetts, 2015, pp. 815–823.
    45. 45)
      • 49. Mackay, D.J.C., Neal, R.M.: ‘Good codes based on very sparse matrices’ (Springer, Berlin, Heidelberg, 1995), pp. 100–111.
    46. 46)
      • 36. Sutcu, Y., Li, Q., Memon, N.: ‘Protecting biometric templates with sketch: theory and practice’, IEEE Trans. Inf. Forensics Sec., 2007, 2, (3), pp. 503–512.
    47. 47)
      • 16. Wang, S., Deng, G., Hu, J.: ‘A partial Hadamard transform approach to the design of cancelable fingerprint templates containing binary biometric representations’, Pattern Recognit., 2017, 61, pp. 447–458.
    48. 48)
      • 47. Rebuffi, S.A., Kolesnikov, A., Sperl, G., et al: ‘iCaRL: incremental classifier and representation learning’. IEEE Conf. on Computer Vision and Pattern Recognition, Honolulu, Hawaii, 2017, pp. 5533–5542.
    49. 49)
      • 8. Sapkal, S., Deshmukh, R.R.: ‘Biometric template protection with fuzzy vault and fuzzy commitment’. Int. Conf. on Information and Communication Technology for Competitive Strategies, Lecce, Italy, 2016, pp. 60–65.
    50. 50)
      • 9. Shao, X., Xu, H., Veldhuis, R.N.J., et al: ‘A concatenated coding scheme for biometric template protection’. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Kyoto, Japan, 2012, pp. 1865–1868.
    51. 51)
      • 14. Teoh, A.B., Goh, A., Ngo, D.C.: ‘Random multispace quantization as an analytic mechanism for biohashing of biometric and random identity inputs’, IEEE Trans. Pattern Anal. Mach. Intell., 2006, 28, (12), pp. 1892–1901.
    52. 52)
      • 39. Jindal, A.K., Chalamala, S., Kumar Jami, S.: ‘Face template protection using deep convolutional neural network’. IEEE Conf. on Computer Vision and Pattern Recognition Workshops, Salt Lake City, Utah, 2018, pp. 426–470.
    53. 53)
      • 25. Wu, W., Kan, M., Liu, X., et al: ‘Recursive spatial transformer (ReST) for alignment-free face recognition’. IEEE Int. Conf. on Computer Vision, Honolulu, Hawaii, 2017, pp. 3772–3780.
    54. 54)
      • 35. Le, T.T.B., Dang, T.K., Truong, Q.C., et al: ‘Protecting biometric features by periodic function-based transformation and fuzzy vault’, ‘Transactions on large-scale data-and knowledge-centered systems XVI’ (Springer, Berlin, Heidelberg, 2014), pp. 5770.
    55. 55)
      • 21. Taigman, Y., Yang, M., Ranzato, M., et al: ‘DeepFace: closing the gap to human-level performance in face verification’. IEEE Conf. on Computer Vision and Pattern Recognition, Columbus, Ohio, 2014, pp. 1701–1708.
    56. 56)
      • 32. Nazari, S., Moin, M.S., Kanan, H.R.: ‘A discriminant binarization transform using genetic algorithm and error-correcting output code for face template protection’, Int. J. Mach. Learn. Cybern., 2017, pp. 1–17, https://doi.org/10.1007/s13042-017-0723-3.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2018.5156
Loading

Related content

content/journals/10.1049/iet-bmt.2018.5156
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address