We've updated our Privacy Policy to make it clearer how we use your personal data.

We use cookies to provide you with a better experience, read our Cookie Policy

Advertisement

AI Watermarks Could Outsmart "Deep Fake" Photos

News   May 30, 2019 | Original story from the NYU Tandon School of Engineering

 
AI Watermarks Could Outsmart "Deep Fake" Photos

In tests, a prototype watermark pipeline increased the ability to detect manipulation from approximately 45 percent to over 90 percent without sacrificing image quality. Credit: NYU Tandon

 
 
Advertisement
 

RELATED ARTICLES

PFASs Found To Impact Estrogen-Controlled Gene Expression

News

Researchers have used a combination of laboratory experiments and computer modeling to reveal that PFASs can interact with the estrogen receptor in different ways to influence estrogen-controlled gene expression.

READ MORE

Deep Learning Model Helps Drug Developers Target SARS-CoV-2's Main Protease

News

Researchers have deployed a machine learning model to help drug developers on their most promising leads for attacking one of the virus’ most compelling targets –SARS-CoV-2's main protease.

READ MORE

Structure of Potent Antibody Against SARS-CoV-2 Is Mapped

News

Scientists at Fred Hutchinson Cancer Research Center in Seattle have shown that a potent antibody from a COVID-19 survivor interferes with a key feature on the surface of the coronavirus’s distinctive spikes, causing them to drop off.

READ MORE

 

To personalize the content you see on Technology Networks homepage, Log In or Subscribe for Free

LOGIN SUBSCRIBE FOR FREE