Abstract
There is a strong positive correlation between the development of deep learning and the amount of public data available. Not all data can be released in their raw form because of the risk to the privacy of the related individuals. The main objective of privacy-preserving data publication is to anonymize the data while maintaining their utility. In this paper, we propose a privacy-preserving semi-generative adversarial network (PPSGAN) that selectively adds noise to class-independent features of each image to enable the processed image to maintain its original class label. Our experiments on training classifiers with synthetic datasets anonymized with various methods confirm that PPSGAN shows better utility than other conventional methods, including blurring, noise-adding, filtering, and generation using GANs.
Highlights
The publication of various benchmark datasets enabled the emergence of a variety of current state-of-the-art deep learning models
We evaluate the quality and the utility of the image data anonymized with our model from different aspects, including the performance of the classifiers trained with the original data, processed with privacy-preserving semi-generative adversarial network (PPSGAN), and generated or modified with other methods
We present a privacy-preserving semi-generative adversarial network (PPSGAN), a methodology to selectively anonymize class-independent features of an image at the latent-space-level
Summary
The publication of various benchmark datasets enabled the emergence of a variety of current state-of-the-art deep learning models. We use the self-attention mechanism [18] to make the noise amplifier of PPSGAN apply different levels of privacy according to the importance of the feature. This mechanism allows PPSGAN to keep the original class label of each image, even in strict privacy conditions. We evaluate the quality and the utility of the image data anonymized with our model from different aspects, including the performance of the classifiers trained with the original data, processed with PPSGAN, and generated or modified with other methods. The encoder and decoder networks add noise to class-independent features of the input image, and the critic and classifier networks evaluate the processed image via comparison with real samples.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
