NYU Tandon researchers implant “digital watermarks” using a neural network to easily spot manipulated photos and video.
To thwart sophisticated methods of altering photos and video, researchers at the NYU Tandon School of Engineering have demonstrated an experimental technique to authenticate images throughout the entire pipeline, from acquisition to delivery, using artificial intelligence (AI).
In tests, this prototype imaging pipeline increased the chances of detecting manipulation from approximately 45 percent to over 90 percent without sacrificing image quality.
Determining whether a photo or video is authentic is becoming increasingly problematic. Sophisticated techniques for altering photos and videos have become so accessible that so-called “deep fakes” — manipulated photos or videos that are remarkably convincing and often include celebrities or political figures — have become commonplace.
Pawel Korus, a research assistant professor in the Department of Computer Science and Engineering at NYU Tandon, pioneered this approach. It replaces the typical photo development pipeline with a neural network — one form of AI — that introduces carefully crafted artifacts directly into the image at the moment of image acquisition. These artifacts, akin to “digital watermarks,” are extremely sensitive to manipulation.
“Unlike previously used watermarking techniques, these AI-learned artifacts can reveal not only the existence of photo manipulations, but also their character,” Korus said.
The process is optimized for in-camera embedding and can survive image distortion applied by online photo sharing services.
The advantages of integrating such systems into cameras are clear.
“If the camera itself produces an image that is more sensitive to tampering, any adjustments will be detected with high probability,” said Nasir Memon, a professor of computer science and engineering at NYU Tandon and co-author, with Korus, of a paper detailing the technique. “These watermarks can survive post-processing; however, they’re quite fragile when it comes to modification: If you alter the image, the watermark breaks,” Memon said.
Most other attempts to determine image authenticity examine only the end product — a notoriously difficult undertaking.
Korus and Memon, by contrast, reasoned that modern digital imaging already relies on machine learning. Every photo taken on a smartphone undergoes near-instantaneous processing to adjust for low light and to stabilize images, both of which take place courtesy of onboard AI. In the coming years, AI-driven processes are likely to fully replace the traditional digital imaging pipelines. As this transition takes place, Memon said that “we have the opportunity to dramatically change the capabilities of next-generation devices when it comes to image integrity and authentication. Imaging pipelines that are optimized for forensics could help restore an element of trust in areas where the line between real and fake can be difficult to draw with confidence.”
Korus and Memon note that while their approach shows promise in testing, additional work is needed to refine the system. This solution is open-source and can be accessed at https://github.com/pkorus/neural-imaging. The researchers will present their paper, “Content Authentication for Neural Imaging Pipelines: End-to-end Optimization of Photo Provenance in Complex Distribution Channels,” at the Conference on Computer Vision and Pattern Recognition in Long Beach, California, in June.
The Latest on: Digital watermarks
via Google News
The Latest on: Digital watermarks
- Digimarc Participates in Procter & Gamble's HolyGrail 2.0 Pavilion Session at World Economic Forumon January 20, 2020 at 4:00 am
/PRNewswire/ -- WHAT: Digimarc Corporation (NASDAQ: DMRC), creator of the Digimarc Platform for digital identification and detection, will be participating ...
- Women Who Lead: Ann Barlowon January 16, 2020 at 3:07 pm
Her personal passions are executive presentation coaching, crisis management, and digital communications. A graduate of the University of Illinois, Barlow is on the board of Illini West and is past ...
- DHL Global Forwarding partners with Xylem Watermark for critical aid shipments and humanitarian logistics support around the worldon January 16, 2020 at 7:00 am
This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20200116005511/en/ “We are excited to officially announce our newest partnership with Xylem ...
- marvel marble: 40 years of monitillo 1980 shown at maison et objet 2020on January 14, 2020 at 2:50 am
wearable technology allows visitors to collect digital coins, fight bosses and compete with one another. the project, which is titled 'watermarks - surviving the anthropocene', highlights the impact ...
- Content Protection And Watermarking Market by Size…on January 14, 2020 at 1:48 am
Thus, present authentic data may be obsolete in the forthcoming period. In addition, some businesses offer their digital watermarking software free of charge and therefore make some of their profit by ...
- Music site Genius sues Google, claiming it caught the company 'red-handed' copying lyricson December 3, 2019 at 1:34 pm
Genius claims in the suit that it found a digital watermark it created in Google's lyric boxes displayed at the top of search results, which are provided through LyricFind. Google and LyricFind have ...
- iQIYI's Self-Developed Watermarking System Passes ChinaDRM Lab's Evaluation Test, Marked as Another Breakthrough in Copyright Protectionon November 18, 2019 at 12:39 am
When a suspected piracy occurs, it can identify the copyright owner through watermark extraction and detection, achieving the purpose of copyright protection. Digital rights management (DRM) ...
- How To Make A Watermark For Your Client Photoson November 6, 2019 at 12:48 pm
What is a Watermark, and Why Should I Use It? A watermark is a kind of stamp, usually low opacity, that is placed on top of digital images. The stamp usually consists of a name, logo, or signature ...
- Digital Forensics and Watermarkingon October 21, 2019 at 5:00 pm
This book constitutes the refereed proceedings of the 17th International Workshop on Digital Forensics and Watermarking, IWDW 2018, held on Jeju Island, Korea, in October 2018.The 25 papers presented ...
- Digimarc to Speak at HolyGrail 2.0 Circular Plastic Economy Eventon October 10, 2019 at 2:09 am
HolyGrail 2.0 aims to speed up the transition to a circular economy for plastics by increasing the quantity and quality of recyclable material identification in waste management systems via ...
via Bing News