Press Release
Posted: March 3, 2021
BROOKLYN, New York, Tuesday, March 2, 2021 – Machine-learning (ML) systems are becoming pervasive not only in technologies affecting our day-to-day lives, but also in those observing them, including face expression recognition systems. Companies that make and use such widely deployed services rely on so-called privacy preservation tools that often use generative adversarial networks (GANs), typically produced by a third party to scrub images of individuals’ identity. But how good are they?
,” presented last month at the 35
th AAAI Conference on Artificial Intelligence, a team led by Siddharth Garg, Institute Associate Professor of electrical and computer engineering at NYU Tandon, explored whether private data could still be recovered from images that had been “sanitized” by such deep-learning discriminators as privacy protecting GANs (PP-GANs) and that had even passed empirical tests. The team, including lead author
4 March 2021, 2:00 am EST By
The impact of machine-learning in the current day has been much evident with its widespread application. For instance, face-recognition systems have been sought for convenience in detecting data, as companies wanted the ease of use of the technology to save time and resources.
However, others rely on privacy-preserving tools which rely on GANs or generative adversarial networks. GANs utilizes neural networks where materials like videos, images, speech, texts, and others can be created. Are they reliable enough to preserve private data?
What the Study Tells About Privacy-Preserving, Machine-Learning Tools
(Photo : Pixabay from Pexels)
Privacy-preservation tools have still a long way to go to retrieve private data from images.
In Subverting Privacy-Preserving GANs: Hiding Secrets in Sanitized Images, researchers at the NYU Tandon School of Engineering led by Siddharth Garg, professor of electrical and computer engineering, explored whether private data could still be recovered from images that had been sanitized by such deep-learning discriminators as privacy protecting GANs (PP-GANs).