Unrecognizable Yet Identifiable: Image Distortion with Preserved Embeddings
This addresses privacy concerns in biometric systems by enabling secure storage of distorted images without compromising verification accuracy, though it is incremental as it builds on existing transformation methods.
The paper tackles the problem of balancing privacy and integrity in biometric authentication by introducing an image transformation technique that distorts facial images to be unrecognizable to humans while preserving identifiability by neural networks, achieving over 70% image content change with maintained recognition accuracy on LFW and MNIST datasets.
Biometric authentication systems play a crucial role in modern security systems. However, maintaining the balance of privacy and integrity of stored biometrics derivative data while achieving high recognition accuracy is often challenging. Addressing this issue, we introduce an innovative image transformation technique that effectively renders facial images unrecognizable to the eye while maintaining their identifiability by neural network models, which allows the distorted photo version to be stored for further verification. While initially intended for biometrics systems, the proposed methodology can be used in various artificial intelligence applications to distort the visual data and keep the derived features close. By experimenting with widely used datasets LFW and MNIST, we show that it is possible to build the distortion that changes the image content by more than 70% while maintaining the same recognition accuracy. We compare our method with previously state-of-the-art approaches. We publically release the source code.