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
- castLabs, ContentArmor and CineSend deliver DRM-protected content with forensic watermarking at over 100 virtual film festivals worldwideon October 1, 2020 at 12:00 am
PRNewswire/ -- castLabs, secure digital video delivery solutions provider, ContentArmor the bitstream watermarking vendor and BitCine Technologies ...
- Storyblocks launches DIY tool to up-level Instagram, TikTok, YouTube contenton September 29, 2020 at 6:00 am
Video creation skills have become essential for anyone who publishes content on the web in order to keep up with exploding global demand for visual digital content.But if you are short on skills, a ...
- Digital watermarks: PepsiCo, Nestlé, and Unilever back sorting tech for packaging recyclingon September 18, 2020 at 8:23 am
Digital watermarks were first discovered under the Ellen MacArthur Foundations’ New Plastics Economy programme. The recently launched pilot project, titled HolyGrail 2.0, aims to build the ...
- Digimarc at Center of Pan-European Development of Digital Watermarking for Improved Plastic Sortation and Recyclingon September 10, 2020 at 11:40 am
It is great to see the potential that intelligent packaging brings, as well as the role that digital watermarking technology can play in the fields of innovation, sustainability and digital ...
- Henkel pioneers digital watermark technologyon September 8, 2020 at 3:40 pm
As a pilot project, Henkel will explore this innovative digital watermark technology for a new product range of its fabric softener brand Vernel. One of the most pressing challenges in achieving a ...
- HolyGrail 2.0 Launched - Mondi Trials Digital Watermarking to Separate Waste for A Circular Economyon September 8, 2020 at 11:48 am
AIM, the European Brands Association, has launched HolyGrail 2.0 with Mondi and other partners across the value chain to prove the viability of digital watermarking for sorting waste at scale. • ...
- European Brands Association's HolyGrail 2.0 tests viability of digital watermarking technologieson September 8, 2020 at 9:40 am
The European Brands Association (AIM), Brussels, has launched HolyGrail 2.0, a pilot project aimed at proving the viability of digital watermarking technologies for accurately sorting recyclables.
- HolyGrail watermarks trialled in quest for easier sortingon September 8, 2020 at 4:36 am
Packaging and paper group Mondi is to conduct full-scale industrial trials to prove digital watermarking could be viable for sorting waste at scale. The watermarks could mean the sorting of dry ...
- HolyGrail 2.0: Major brands sign up to explore digital watermarks to improve packaging recyclingon September 7, 2020 at 5:00 pm
More than 80 major European brands, including P&G, PepsiCo and Mondi will collaborate to explore the feasibility of using "digital watermarks" to improve the sorting of recyclable packaging across the ...
via Bing News