Integrating Utility into Face De-identification

  • Ralph Gross
  • Edoardo Airoldi
  • Bradley Malin
  • Latanya Sweeney
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3856)


With the proliferation of inexpensive video surveillance and face recognition technologies, it is increasingly possible to track and match people as they move through public spaces. To protect the privacy of subjects visible in video sequences, prior research suggests using ad hoc obfuscation methods, such as blurring or pixelation of the face. However, there has been little investigation into how obfuscation influences the usability of images, such as for classification tasks. In this paper, we demonstrate that at high obfuscation levels, ad hoc methods fail to preserve utility for various tasks, whereas at low obfuscation levels, they fail to prevent recognition. To overcome the implied tradeoff between privacy and utility, we introduce a new algorithm, k-Same-Select, which is a formal privacy protection schema based on k-anonymity that provably protects privacy and preserves data utility. We empirically validate our findings through evaluations on the FERET database, a large real world dataset of facial images.


Face Recognition Recognition Rate Face Image Recognition Accuracy Privacy Protection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Belsie, L.: The eyes have it - for now. Christian Science Monitor (November 7, 2002)Google Scholar
  2. 2.
    Sweeney, L.: Surveillance of surveillance camera watch project (2004)Google Scholar
  3. 3.
    Bowyer, K.: Face recognition technology and the security vs. privacy tradeoff. IEEE Technology and Society, 9–20 (2004)Google Scholar
  4. 4.
    Crowley, J., Coutaz, J., Berard, F.: Things that see. Communications of the ACM 43, 54–64 (2000)CrossRefGoogle Scholar
  5. 5.
    Neustaedter, C., Greenberg, S.: Balancing privacy and awareness in home media spaces. In: Dey, A.K., Schmidt, A., McCarthy, J.F. (eds.) UbiComp 2003. LNCS, vol. 2864. Springer, Heidelberg (2003)Google Scholar
  6. 6.
    Newton, E., Sweeney, L., Malin, B.: Preserving privacy by de-identifying facial images. IEEE Transactions on Knowledge and Data Engineering 17, 232–243 (2005)CrossRefGoogle Scholar
  7. 7.
    Boyle, M., Edwards, C., Greenberg, S.: The effects of filtered video on awareness and privacy. In: ACM Conference on Computer Supported Cooperative Work, Philadelphia, PA, pp. 1–10 (2000)Google Scholar
  8. 8.
    Greenberg, S., Kuzuoka, H.: Using digital but physical surrogates to mediate awareness, communication, and privacy in media spaces. Personal Technologies 4 (2000)Google Scholar
  9. 9.
    Hudson, S., Smith, I.: Techniques for addressing fundamental privacy and disruption tradeoffs in awareness support systems. In: ACM Conference on Computer Supported Cooperative Work, Boston, MA, pp. 1–10 (1996)Google Scholar
  10. 10.
    Neustaedter, C., Greenberg, S., Boyle, M.: Blur filtration fails to preserve privacy for home-based video conferencing. ACM Transactions on Computer Human Interactions (TOCHI) (in press, 2005)Google Scholar
  11. 11.
    Zhao, Q., Stasko, J.: Evaluating image filtering based techniques in media space applications. In: ACM Conference on Computer Supported Cooperative Work, Seattle, WA, pp. 11–18 (1998)Google Scholar
  12. 12.
    Senior, A., Pankati, S., Hampapur, A., Brown, L., Tian, Y.L., Ekin, A.: Blinkering surveillance: enabling video surveillance privacy through computer vision. IBM Research Report RC22886 (W0308-109), T.J. Watson Research Center, Yorktown Heights (2003)Google Scholar
  13. 13.
    Alexander, J., Kenny, S.: Engineering privacy in public: Confounding face recognition. In: Dingledine, R. (ed.) PET 2003. LNCS, vol. 2760, pp. 88–106. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  14. 14.
    Sweeney, L.: k-anonymity: a model for protecting privacy. International Journal on Uncertainty, Fuzziness, and Knowledge-Based Systems 10, 557–570 (2002)MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Kanade, T.: Computer Recognition of Human Faces. Birkhauser, Basel (1977)CrossRefGoogle Scholar
  16. 16.
    Zhao, W., Chellappa, R., Phillips, P., Rosenfeld, A.: Face recognition: a literature survey. ACM Computing Surveys 35, 399–458 (2003)CrossRefGoogle Scholar
  17. 17.
    Gross, R., Shi, J., Cohn, J.: Quo vadis face recognition? In: Third Workshop on Empirical Evaluation Methods in Computer Vision (2001)Google Scholar
  18. 18.
    Blackburn, D., Bone, M., Philips, P.: Facial recognition vendor test 2000: evaluation report (2000)Google Scholar
  19. 19.
    Phillips, P.J., Grother, P., Ross, J.M., Blackburn, D., Tabassi, E., Bone, M.: Face recognition vendor test 2002: evaluation report (2003)Google Scholar
  20. 20.
    Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence 19, 711–720 (1997)CrossRefGoogle Scholar
  21. 21.
    Penev, P., Atick, J.: Local feature analysis: A general statistical theory for object representation (1996)Google Scholar
  22. 22.
    Gross, R., Yang, J., Waibel, A.: Face recognition in a meeting room. In: Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition, Grenoble, France (2000)Google Scholar
  23. 23.
    Phillips, P.J., Wechsler, H., Huang, J.S., Rauss, P.J.: The FERET database and evaluation procedure for face-recognition algorithms. Image and Vision Computing 16, 295–306 (1998)CrossRefGoogle Scholar
  24. 24.
    Sonka, M., Hlavac, V., Boyle, R.: Image processing, analysis, and machine vision. 2nd edn. Brooks/Cole (1999)Google Scholar
  25. 25.
    Cristianini, N., Shawe-Taylor, J.: An introduction to support vector machines. Cambridge University Press, Cambridge (2000)zbMATHGoogle Scholar
  26. 26.
    Seeger, M.: Learning with labeled and unlabeled data. Technical report, University of Edinburgh (2002)Google Scholar
  27. 27.
    Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: COLT: Proceedings of the Workshop on Computational Learning Theory. Morgan Kaufmann Publishers, San Francisco (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Ralph Gross
    • 1
  • Edoardo Airoldi
    • 1
  • Bradley Malin
    • 1
  • Latanya Sweeney
    • 1
  1. 1.Data Privacy Laboratory, School of Computer ScienceCarnegie Mellon UniversityPittsburghUSA

Personalised recommendations