Maximum Entropy Binary Encoding for Face Template Protection
This addresses the problem of template security and cancelability for face authentication systems, offering a practical solution with strong performance, though it is incremental in applying existing hashing techniques to a new encoding method.
The paper tackles secure face authentication by proposing a framework that maps face images to maximum entropy binary codes using CNNs, then hashes them for template protection, achieving high genuine accept rates (~95%) at zero false accept rate with up to 1024 bits of security on standard face databases.
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 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 (similar to text based password protection). The algorithm makes no unrealistic assumptions and offers high template security, cancelability, and state-of-the-art matching performance. 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) with up to 1024 bits of template security.