Maximum Entropy Binary Encoding for Face Template Protection

Pandey, Rohit; Zhou, Yingbo; Kota, Bhargava Urala; Govindaraju, Venu

doi:10.48550/arxiv.1512.01691

Cited by 1 publication

(18 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples of NN-learned face BTP methods in the literature, include: [37]- [51]. Recall that methods in this category use a neural network to learn the BTP algorithm, instead of explicitly formulating it like Non-NN BTP methods.…”

Section: Feature-levelmentioning

confidence: 99%

“…Examples of NN-learned face BTP methods that pre-define a representative binary code (and cryptographically hash it to produce the protected template), include [37]- [42]. Of these, [37]- [39] adopt an image-level approach, whereby the NN is trained in an end-to-end manner to map the input face images to their corresponding, pre-defined codes. Alternatively, [40]- [42] adopt a feature-level approach, where the NN training starts from the extracted face features as opposed to the raw images.…”

Section: Feature-levelmentioning

confidence: 99%

“…Alternatively, [40]- [42] adopt a feature-level approach, where the NN training starts from the extracted face features as opposed to the raw images. Overall, most of these methods build upon the approach proposed in [37], [38], which involves assigning a random maximum-entropy binary code to every user of the face recognition system, then training a Convolutional Neural Network (CNN) to map each user's face image to their corresponding code. The trained CNN should be able to deal with natural variations across different face images acquired from the same user, producing the same code during enrollment and each authentication attempt.…”

Section: Feature-levelmentioning

confidence: 99%

“…Another approach towards improving the BTP method in [37], [38] was proposed in [40]. This work adopts a deeper CNN consisting of two components: a pre-trained DNN that is used to extract face features from the input face images, followed by a second NN that maps the extracted face features to the user's pre-defined binary code.…”

Section: Feature-levelmentioning

confidence: 99%

“…Further improvements to the BTP approach in [37], [38], also based on feature-level NN training, were proposed in [41], [42]. Both suggestions for improvement mainly focus on the addition of extra, user-specific information to incorporate more complexity into the mapping between a user's face features and their pre-defined (pre-hash) code.…”

Section: Feature-levelmentioning

confidence: 99%

See 4 more Smart Citations

Biometric Template Protection for Neural-Network-based Face Recognition Systems: A Survey of Methods and Evaluation Techniques

Hahn¹,

Marcel²

2021

Preprint

View full text Add to dashboard Cite

As automated face recognition applications tend towards ubiquity, there is a growing need to secure the sensitive face data used within these systems. This paper presents a survey of biometric template protection (BTP) methods proposed for securing face "templates" (images or representative features) in neural-network-based face recognition systems. The BTP methods are categorised into two types: Non-NN and NN-learned. Non-NN methods use a neural network (NN) as a feature extractor, but the BTP part is based on a non-NN algorithm applied at either image-level or feature-level. In contrast, NN-learned methods specifically employ a NN to learn a protected template from the unprotected face image or features. We present examples of Non-NN and NN-learned face BTP methods from the literature, along with a discussion of the two categories' comparative strengths and weaknesses. We also investigate the techniques used to evaluate these BTP methods, in terms of the three most common BTP criteria: "recognition accuracy", "irreversibility", and "renewability/unlinkability". As expected, the recognition accuracy of protected face recognition systems is generally evaluated using the same (empirical) techniques employed for evaluating standard (unprotected) biometric systems. On the contrary, most irreversibility and renewability/unlinkability evaluations are found to be based on theoretical assumptions/estimates or verbal implications, with a lack of empirical validation in a practical face recognition context. We recommend, therefore, a greater focus on empirical evaluation strategies, to provide more concrete insights into the irreversibility and renewability/unlinkability of face BTP methods in practice. Additionally, an exploration of the reproducibility of the studied BTP works, in terms of the public availability of their implementation code and evaluation datasets/procedures, suggests that it would currently be difficult for the BTP community to faithfully replicate (and thus validate) most of the reported findings. So, we advocate for a push towards reproducibility, in the hope of furthering our understanding of the face BTP research field.

show abstract

Section: Feature-levelmentioning

confidence: 99%