Privacy of Facial Soft Biometrics: Suppressing Gender But Retaining Identity

We consider the problem of perturbing a face image in such a way that it cannot be used to ascertain soft biometric attributes such as age, gender and race, but can be used for automatic face recognition. Such an exercise is useful for extending different levels of privacy to a face image in a central database. In this work, we focus on masking the gender information in a face image with respect to an automated gender estimation scheme, while retaining its ability to be used by a face matcher. To facilitate this privacy-enhancing technique, the input face image is combined with another face image via a morphing scheme resulting in a mixed image. The mixing process can be used to progressively modify the input image such that its gender information is progressively suppressed; however, the modified images can still be used for recognition purposes if necessary. Preliminary experiments on the MUCT database suggest the potential of the scheme in imparting “differential privacy” to face images.

[1]  Ninghui Li,et al.  t-Closeness: Privacy Beyond k-Anonymity and l-Diversity , 2007, 2007 IEEE 23rd International Conference on Data Engineering.

[2]  Stephen Milborrow.  The MUCT Landmarked Face Database , 2010 .

[3]  Vitaly Shmatikov,et al.  Robust De-anonymization of Large Sparse Datasets , 2008, 2008 IEEE Symposium on Security and Privacy (sp 2008).

[4]  Arun Ross,et al.  On Mixing Fingerprints , 2013, IEEE Transactions on Information Forensics and Security.

[5]  Anil K. Jain,et al.  Ethnicity identification from face images , 2004, SPIE Defense + Commercial Sensing.

[6]  Bradley Malin,et al.  Preserving privacy by de-identifying face images , 2005, IEEE Transactions on Knowledge and Data Engineering.

[7]  Andreas Uhl,et al.  A survey on biometric cryptosystems and cancelable biometrics , 2011, EURASIP J. Inf. Secur..

[8]  Nalini K. Ratha,et al.  Enhancing security and privacy in biometrics-based authentication systems , 2001, IBM Syst. J..

[9]  Yun Fu,et al.  Age Synthesis and Estimation via Faces: A Survey , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Wen Gao,et al.  High-Resolution Face Fusion for Gender Conversion , 2011, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[11]  Andreas Uhl,et al.  Cancelable Iris Biometrics Using Block Re-mapping and Image Warping , 2009, ISC.

[12]  Duncan Rowland,et al.  Manipulating Facial Appearance through , 1995 .

[13]  Ashwin Machanavajjhala,et al.  l-Diversity: Privacy Beyond k-Anonymity , 2006, ICDE.

[14]  Ramakrishnan Srikant,et al.  Privacy-preserving data mining , 2000, SIGMOD '00.

[15]  Nalini K. Ratha,et al.  Cancelable iris biometric , 2008, 2008 19th International Conference on Pattern Recognition.

[16]  Latanya Sweeney,et al.  k-Anonymity: A Model for Protecting Privacy , 2002, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[17]  Andreas Uhl,et al.  Transforming Rectangular and Polar Iris Images to Enable Cancelable Biometrics , 2010, ICIAR.

[18]  Rakesh Agrawal,et al.  Privacy-preserving data mining , 2000, SIGMOD 2000.

[19]  Roope Raisamo,et al.  Evaluation of Gender Classification Methods with Automatically Detected and Aligned Faces , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Cynthia Dwork,et al.  Differential Privacy , 2006, ICALP.

[21]  Ralph Gross,et al.  Model-Based Face De-Identification , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[22]  George Wolberg,et al.  Image morphing: a survey , 1998, The Visual Computer.