Forbes: Face Obfuscation Rendering via Backpropagation Refinement Scheme
This addresses privacy concerns in facial recognition systems by enabling selective obfuscation, though it appears incremental as it builds on existing transformation and optimization techniques.
The paper tackles the problem of face obfuscation by developing Forbes, an algorithm that renders images unrecognizable to humans while preserving identity for machines, achieving excellent results in experiments on various datasets.
A novel algorithm for face obfuscation, called Forbes, which aims to obfuscate facial appearance recognizable by humans but preserve the identity and attributes decipherable by machines, is proposed in this paper. Forbes first applies multiple obfuscating transformations with random parameters to an image to remove the identity information distinguishable by humans. Then, it optimizes the parameters to make the transformed image decipherable by machines based on the backpropagation refinement scheme. Finally, it renders an obfuscated image by applying the transformations with the optimized parameters. Experimental results on various datasets demonstrate that Forbes achieves both human indecipherability and machine decipherability excellently. The source codes are available at https://github.com/mcljtkim/Forbes.