Machine learning systems are becoming pervasive in technologies affecting our day-to-day lives, including face expression recognition systems. Machine-learning-based privacy tools have broad applicability, potentially in any privacy sensitive domain. Researchers explored whether private data could still be recovered from images that had been sanitized by such deep-learning discriminators as privacy protecting GANs. They found that PP-GAN designs can, in fact, be subverted to pass privacy checks, while still allowing secret information to be extracted from sanitized images.
Source: https://www.helpnetsecurity.com/2021/03/12/recover-data-sanitized-images/