Suppressing Gender and Age in Face Templates Using Incremental Variable Elimination

Recent research on soft-biometrics showed that more information than just the person’s identity can be deduced from biometric data. Using face templates only, information about gender, age, ethnicity, health state of the person, and even the sexual orientation can be automatically obtained. Since for most applications these templates are expected to be used for recognition purposes only, this raises major privacy issues. Previous work addressed this problem purely on image level regarding function creep attackers without knowledge about the systems privacy mechanism. In this work, we propose a soft-biometric privacy enhancing approach that reduces a given biometric template by eliminating its most important variables for predicting soft-biometric attributes. Training a decision tree ensemble allows deriving a variable importance measure that is used to incrementally eliminate variables that allow predicting sensitive attributes. Unlike previous work, we consider a scenario of function creep attackers with explicit knowledge about the privacy mechanism and evaluated our approach on a publicly available database. The experiments were conducted to eight baseline solutions. The results showed that in many cases IVE is able to suppress gender and age to a high degree with a negligible loss of the templates recognition ability. Contrary to previous work, which is limited to the suppression of binary (gender) attributes, IVE is able, by design, to suppress binary, categorical, and continuous attributes.

[1]  Richa Singh,et al.  Anonymizing k-Facial Attributes via Adversarial Perturbations , 2018, IJCAI.

[2]  Terrance E. Boult,et al.  Facial Attributes: Accuracy and Adversarial Robustness , 2017, Pattern Recognit. Lett..

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

[4]  Arun Ross,et al.  Gender Privacy: An Ensemble of Semi Adversarial Networks for Confounding Arbitrary Gender Classifiers , 2018, 2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS).

[5]  Bipin Kumar Tripathi,et al.  On the complex domain deep machine learning for face recognition , 2017, Applied Intelligence.

[6]  Arun Ross,et al.  What Else Does Your Biometric Data Reveal? A Survey on Soft Biometrics , 2016, IEEE Transactions on Information Forensics and Security.

[7]  Xiaoming Liu,et al.  Attribute preserved face de-identification , 2015, 2015 International Conference on Biometrics (ICB).

[8]  Naser Damer,et al.  CrazyFaces: Unassisted Circumvention of Watchlist Face Identification , 2018, 2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS).

[9]  Bhiksha Raj,et al.  SphereFace: Deep Hypersphere Embedding for Face Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  K. M. Bhurchandi,et al.  Expression invariant face recognition using semidecimated DWT, Patch-LDSMT, feature and score level fusion , 2015, Applied Intelligence.

[11]  Terrance E. Boult,et al.  Are facial attributes adversarially robust? , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

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

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

[14]  Els Kindt.  Biometric Data, Data Protection and the Right to Privacy , 2013 .

[15]  Gilles Louppe,et al.  Understanding variable importances in forests of randomized trees , 2013, NIPS.

[16]  Arun Ross,et al.  Soft biometric privacy: Retaining biometric utility of face images while perturbing gender , 2017, 2017 IEEE International Joint Conference on Biometrics (IJCB).

[17]  ASHWIN MACHANAVAJJHALA,et al.  L-diversity: privacy beyond k-anonymity , 2006, 22nd International Conference on Data Engineering (ICDE'06).

[18]  Arun Ross,et al.  Privacy of Facial Soft Biometrics: Suppressing Gender But Retaining Identity , 2014, ECCV Workshops.

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

[20]  Jiang-She Zhang,et al.  Robust face recognition via discriminative and common hybrid dictionary learning , 2017, Applied Intelligence.

[21]  S. R. Mahadeva Prasanna,et al.  Speech biometric based attendance system , 2014, 2014 Twentieth National Conference on Communications (NCC).

[22]  Naser Damer,et al.  Detecting Face Morphing Attacks by Analyzing the Directed Distances of Facial Landmarks Shifts , 2018, GCPR.

[23]  Peter Peer,et al.  Selective Face Deidentification with End-to-End Perceptual Loss Learning , 2018, 2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI).

[24]  Davis E. King.  Max-Margin Object Detection , 2015, ArXiv.

[25]  Naser Damer,et al.  Unsupervised privacy-enhancement of face representations using similarity-sensitive noise transformations , 2019, Applied Intelligence.

[26]  Roberto J. Bayardo,et al.  Data privacy through optimal k-anonymization , 2005, 21st International Conference on Data Engineering (ICDE'05).

[27]  M. Kosinski,et al.  Deep Neural Networks Are More Accurate Than Humans at Detecting Sexual Orientation From Facial Images , 2018, Journal of personality and social psychology.

[28]  Hyeonjoon Moon,et al.  The FERET evaluation methodology for face-recognition algorithms , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[29]  Arun Ross,et al.  Semi-adversarial Networks: Convolutional Autoencoders for Imparting Privacy to Face Images , 2017, 2018 International Conference on Biometrics (ICB).

[30]  Ramachandra Raghavendra,et al.  Biometric Authentication Protocols on Smartphones: An Overview , 2016, SIN.