Abstract | ||
---|---|---|
In this paper we present a framework for secure identification using deep neural networks, and apply it to the task of template protection for face password authentication. We use deep convolutional neural networks (CNNs) to learn a mapping from face images to maximum entropy binary (MEB) codes. The mapping is robust enough to tackle the problem of exact matching, yielding the same code for new samples of a user as the code assigned during training. These codes are then hashed using any hash function that follows the random oracle model (like SHA-512) to generate protected face templates. The algorithm makes no unrealistic assumptions and offers high template security, cancelability, and matching performance comparable to the state-of-the-art. The efficacy of the approach is shown on CMU-PIE, Extended Yale B, and Multi-PIE face databases. We achieve high (~ 95%) genuine accept rates (GAR) at zero false accept rate (FAR) while maintaining a high level of template security. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/CVPRW.2016.17 | 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) |
Keywords | Field | DocType |
deep secure encoding,face template protection,secure identification,face password authentication,deep convolutional neural networks,CNN,face images,maximum entropy binary codes,MEB codes,hash function,genuine accept rates,GAR,false accept rate,FAR | Pattern recognition,Convolutional neural network,Computer science,Random oracle,Theoretical computer science,Artificial intelligence,Hash function,Password authentication protocol,Template,Principle of maximum entropy,Encoding (memory),Binary number | Conference |
Volume | Issue | ISSN |
2016 | 1 | 2160-7508 |
ISBN | Citations | PageRank |
978-1-5090-1438-5 | 2 | 0.37 |
References | Authors | |
18 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rohit Pandey | 1 | 7 | 1.83 |
Yingbo Zhou | 2 | 263 | 19.43 |
Bhargava Urala Kota | 3 | 24 | 1.73 |
Venu Govindaraju | 4 | 3521 | 422.00 |