Deep Secure Encoding for Face Template Protection

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

doi:10.1109/cvprw.2016.17

Cited by 47 publications

(48 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With this work we are specifically focusing on the biometric authentication problem for which, apart from achieving a high recognition accuracy, it is even more crucial to reduce the number of wrongly authorized users. For the same reason, it is common to assume that the user puts him/herself in a controlled condition and as such, the face datasets we consider, are those commonly used for biometric authentication tasks, see [26], [27]. Conversely, recent "inthe-wild" face datasets, because of the large number of users and poses, are better suited for the evaluation of recognition and clustering tasks.…”

Section: Figurementioning

confidence: 99%

Adversarial Learning of Mappings Onto Regularized Spaces for Biometric Authentication

et al. 2020

View full text Add to dashboard Cite

We present AuthNet: a novel framework for generic biometric authentication which, by learning a regularized mapping instead of a classification boundary, leads to higher performance and improved robustness. The biometric traits are mapped onto a latent space in which authorized and unauthorized users follow simple and well-behaved distributions. In turn, this enables simple and tunable decision boundaries to be employed in order to make a decision. We show that, differently from the deep learning and traditional template-based authentication systems, regularizing the latent space to simple target distributions leads to improved performance as measured in terms of Equal Error Rate (EER), accuracy, False Acceptance Rate (FAR) and Genuine Acceptance Rate (GAR). Extensive experiments on publicly available datasets of faces and fingerprints confirm the superiority of AuthNet over existing methods.

show abstract

Section: Figurementioning

confidence: 99%

Adversarial Learning of Mappings Onto Regularized Spaces for Biometric Authentication

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Vizilter et al [38] decoded the output of CNN and then hashed it via a boosted hashing forest. Pandey et al [26] protected face template by mapping original images to a binary code using CNN. Jindal et al [39] used CNN, with one-shot and multi-shot enrolment, to learn a robust mapping from face images of the users to the unique binary codes.…”

Section: Related Workmentioning

confidence: 99%

“…The approach such as [26] usually maps the outputs of CNN to [0, 1] by sigmoid function and then uses a threshold to decide the where r k and l k denote the kth element of R and L m , respectively. We find that the distribution of noise follows the Gaussian distribution, which is shown in Fig.…”

Section: Ldpc Decodingmentioning

confidence: 99%

“…Pandey et al . [26] protected face template by mapping original images to a binary code using CNN. Jindal et al .…”

Section: Related Workmentioning

confidence: 99%

“…With representation learning ability, the convolutional neural network (CNN) is able to achieve state-of-the-art results, as opposed to using handcrafted features. To protect face templates extracted by deep learning method, Pandey et al [26] proposed a deep secure encoding for face template protection. Even though the accuracy of the secure face template is greatly improved by the learned CNN template, there is still a large gap between deep learning-based face recognition and verification methods without considering template protection.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Face template protection using deep LDPC codes learning

et al. 2019

View full text Add to dashboard Cite

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.

show abstract

A Face Privacy Protection Algorithm Based on Block Scrambling and Deep Learning

Shen

Zhang

2018

Cloud Computing and Security

View full text Add to dashboard Cite

Deep Secure Encoding for Face Template Protection

Cited by 47 publications

References 21 publications

Adversarial Learning of Mappings Onto Regularized Spaces for Biometric Authentication

Adversarial Learning of Mappings Onto Regularized Spaces for Biometric Authentication

Face template protection using deep LDPC codes learning

A Face Privacy Protection Algorithm Based on Block Scrambling and Deep Learning

Contact Info

Product

Resources

About