
via AiThority
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.
Learn more: Outsmarting deep fakes: Researchers devise an AI-driven imaging system that protects authenticity
The Latest on: Digital watermarks
via Google News
The Latest on: Digital watermarks
- Synamedia partners with Akamai to speed pirate take downson January 12, 2021 at 6:02 am
Synamedia, the world's largest independent video software provider, today announced that its security and watermarking solutions are ...
- Synamedia integrates security and watermarking with Akamaion January 12, 2021 at 2:00 am
Synamedia's security and watermarking solutions are now integrated with the Akamai Intelligent Edge Platform. The combination detects pirate streams in real time and redirect viewers to legitimate ...
- Digital.com Names Best Photography Website Builders of 2021on January 4, 2021 at 9:00 pm
Digital.com, a leading independent review website for small business online tools, products, and services, has announced the ...
- Art Notes: Call for artists for Napa County Library's Art in the Library serieson January 2, 2021 at 2:15 pm
The Napa County Library invites California artists to apply to a juried competition with winners’ work to be displayed in January 2022 through December 2022. All two-dimensional work including ...
- New Cultural Awareness Campaign “Not Another Second” Honors LGBT+ Seniors & Advocates for a More Accepting Futureon January 1, 2021 at 10:12 pm
Not Another Second – the first in a national series of cultural campaigns – tells the untold stories of 12 LGBT+ elders and the years they lost not being their fully authentic selves, through a ...
- Library, Watermark stick with virtual and curbside services in Beaver Damon January 1, 2021 at 9:00 am
The Beaver Dam Community Library and Watermark community center will provide virtual and curbside services into the new year.
- Rights reserved: A new digital watermarking method for 3D printing modelson December 31, 2020 at 2:00 am
Senior Content Producer Sam Davies talks to the professor behind the 3D printing industry's latest IP protection patent.
- Digital Kidnapping - A New Online Trend by the WISPYon December 29, 2020 at 9:52 am
It is Time to Discover Some Important Tips to Evade Digital Kidnapping. 1 – Never Share Too Much Information on Social Media We always recommend not to open yourself on social media. Think twice when ...
- Testing photo editing apps: "Typorama for iOS"on December 22, 2020 at 4:59 am
DW Digital tests the most popular apps ... It also features a logo design tool that allows businesses to apply watermarks and brand logos to their designs. The handling is simple: just choose ...
- Removing DRM From Aaron Swartz’s EBookon December 21, 2020 at 4:00 pm
After analyzing several digital copies of Aaron Swartz’s eBook, the Institute for Biblio-Immunology is confident they have a tool that removes BooXtrem’s watermarks in EPUB eBooks. Several ...
via Bing News