Connect with us


MIT’s “PhotoGuard” Protects Images From Unauthorized AI Edits

The technology invisibly alters select pixels to throw off algorithmic AI models.



mit's photoguard protects images from unauthorized ai edits

As AI continues to develop rapidly, chatbots are gaining the power to create and manipulate images, with Shutterstock and Adobe currently leading the way. Despite the obvious power of AI algorithms, the technology has a few pitfalls, one of which is the unauthorized manipulation of copyrighted artwork and images.

MIT CSAIL thinks it has the answer to this growing problem in the form of PhotoGuard, a new technique that alters select pixels in an image to disrupt AI’s ability to understand what the image is.

The altered pixels are known as “perturbations” and are invisible to the human eye but easily seen by AI bots as they scan the color and position of every pixel in an image. Any edits AI tries to make to a protected image will also apply to the fake pixels, resulting in an unrealistic or broken final image, thanks to PhotoGuard.

Also Read: PicSo Review: A Popular AI-Based Text-To-Image App

“The encoder attack makes the model think that the input image is some other image,” explained MIT student and lead author of the paper, Hadi Salman. “Whereas the diffusion attack forces the diffusion model to make edits towards some target image”. The technique sounds complex but could potentially stop malicious actors from reverse engineering protected images by adding minor edits to circumvent copyright.

“A collaborative approach involving model developers, social media platforms, and policymakers presents a robust defense against unauthorized image manipulation. Working on this pressing issue is of paramount importance today,” Salman said in a recent press release. “And while I am glad to contribute towards this solution, much work is needed to make this protection practical. Companies that develop these models need to invest in engineering robust immunizations against the possible threats posed by these AI tools”.


📢 Get Exclusive Monthly Articles, Updates & Tech Tips Right In Your Inbox!


Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *


Adobe Teases New AI Editing Tools And Updates In Premiere Pro

The video editing app will be enhanced with a generative extend tool, text-to-video, improved timeline waveforms, and more.



adobe teases new ai editing tools and updates in premiere pro

After launching the generative AI model Firefly last year, Adobe is now showcasing how the technology will be used in upcoming versions of the editing app Premiere Pro. In an early sneak peek, the company demonstrated several new features, including Object Addition and Removal, Generative Extend, and Text to Video.

The first new feature, Generative Extend, targets a common video editing problem by using AI to “Seamlessly add frames to make clips longer, so it’s easier to perfectly time edits and add smooth transitions”.

Meanwhile, Premiere Pro’s Object Addition & Removal tool will leverage Firefly’s generative AI to “Simply select and track objects, then replace them. Remove unwanted items, change an actor’s wardrobe or quickly add set dressings such as a painting or photorealistic flowers on a desk,” Adobe states.

Adobe also showcased another new feature that can automatically generate new film clips using a text prompt. To use the content creation tool, editors can “Simply type text into a prompt or upload reference images. These clips can be used to ideate and create storyboards, or to create B-roll for augmenting live action footage,” Adobe explained. The company seems to be commercializing this particular feature extremely quickly, considering generative AI video only appeared a few months ago.

Also Read: UGREEN Unveils Nexode RG 65W Charger For Middle East

The new additions to Premiere Pro will be added later this year, but Adobe is also introducing smaller improvements to the editing app in May. The changes include interactive fade handles to enable easier transitions, an Essential Sound badge that uses AI to “automatically tag audio clips as dialogue, music, sound effects or ambience, and add a new icon so editors get one-click, instant access to the right controls for the job”, along with effect badges and a new look for waveforms in the timeline.

Continue Reading