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
[google_news title=”” keyword=”digital watermarks” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Digital watermarks
- Google Watermarking AI-Generated Content: A Dive into SynthIDon May 16, 2024 at 9:39 am
By integrating the watermarking process directly into the AI's output, SynthID ensures that the authenticity signal is retained no ...
- Google's AI Watermarks Will Identify Deepfakeson May 16, 2024 at 6:03 am
The SynthID line of watermarking techniques can be used to identify images, video, and text generated by artificial intelligence.
- Digimarc Appoints Former SAP and Workato HR Executive and Human Capital Strategist Carle Quinn as Chief People Officeron May 15, 2024 at 8:37 am
Digimarc Corporation (NASDAQ: DMRC), the pioneer and global leader in digital watermarking technologies, today announced that former Workato Chief People Officer and human capital strategist Carle ...
- Google’s invisible AI watermark will help identify generative text and videoon May 14, 2024 at 3:04 pm
Among Google’s swath of new AI models and tools announced today, the company is also expanding its AI content watermarking and detection technology to work across two new mediums. Google’s DeepMind ...
- Google expands digital watermarks to AI-made videoon May 14, 2024 at 10:52 am
As Google starts to make its latest video-generation tools available, the company says it has a plan to ensure transparency around the origins of its increasingly realistic AI-generated clips.
- Google SynthID Doubles Down on AI Watermarking with Video and Text Supporton May 14, 2024 at 9:06 am
Google has introduced an updated version of its SynthID system which can now add digital watermarks to texts and videos generated using AI.
- Digital Watermarks: AI's Answer to Deepfake Dilemmason May 14, 2024 at 9:03 am
In an era where AI's capabilities are rapidly advancing, the threat of image misuse and deepfakes is a growing concern. Gabrielle Waters, an AI and machine learning researcher, sheds light ...
- TikTok will label or remove AI-made content from third-party appson May 10, 2024 at 9:40 am
TikTok announced it will begin labeling AI-generated media using digital watermark technology called Content Credentials.
- TikTok to label AI-generated content from OpenAI and elsewhereon May 9, 2024 at 1:38 pm
TikTok plans to start labelling images and video uploaded to its video-sharing service that have been generated using artificial intelligence, it said on Thursday, using a digital watermark known as ...
- TikTok's AI watermarks could help curb deepfakes, but it's no panaceaon May 9, 2024 at 10:46 am
TikTok's new system is designed to detect and disclose when external tools make their way into the app’s feeds.
via Bing News