Embedding Non-Distortive Cancelable Face Template Generation
This addresses privacy and security concerns in biometric systems for authentication applications, but appears incremental as it builds on existing distortion and embedding methods.
The paper tackles the problem of balancing privacy and accuracy in biometric authentication by introducing an image distortion technique that makes facial images unrecognizable to the eye while maintaining identifiability for neural networks, achieving results tested on MNIST and LFW datasets with traditional metrics.
Biometric authentication systems are crucial for security, but developing them involves various complexities, including privacy, security, and achieving high accuracy without directly storing pure biometric data in storage. We introduce an innovative image distortion technique that makes facial images unrecognizable to the eye but still identifiable by any custom embedding neural network model. Using the proposed approach, we test the reliability of biometric recognition networks by determining the maximum image distortion that does not change the predicted identity. Through experiments on MNIST and LFW datasets, we assess its effectiveness and compare it based on the traditional comparison metrics.