Subj : We broke them all How researchers broke current image watermarki To : All From : TechnologyDaily Date : Thu Oct 12 2023 05:30:04 We broke them all How researchers broke current image watermarking protections and what it means for a new era of truth-altering reality Date: Thu, 12 Oct 2023 04:27:57 +0000 Description: Big tech may point to watermarking to separate real from AI-generated material, but scientists have already cracked it. FULL STORY ====================================================================== The tool many big tech companies are banking heavily on being able to help the public and businesses separate fact from fiction, in the context of AIs meteoric rise, has already been undermined before its even taken off. The idea of watermarking is something that companies including OpenAI, Amazon and Google have pointed to as being able to combat disinformation online . With generative AI on the rise , particularly in the form of deepfakes, it might be looked at as one way to identify whats actually real. Its one of the key proposals among efforts to make the usage of AI, safer and more transparent . There arent, however, many clear-cut approaches to watermarking yet that are completely fool-proof or reliable, and professors with the University of Maryland have already found a way to break all of the existing methods, according to TechXplore . How scientists have already cracked AI watermarking The researchers used a technique called diffusion purification to blast Gaussian noise a kind of electronic noise signaling at a watermark to completely remove it, without impacting the underlying image too much. With AI-generated content on the rise, especially in certain industries, the scope for abuse has also surfaced as a very real possibility. Its also essential to find tools and strategies to be able to distinguish genuine content from that made by machines. Watermarking is a promising approach, according to the paper , published on 29 September. It involves hiding a signal in a piece of text or image to determine if its AI-generated. The theory goes a tool you run the content through would then be able to determine whether its real or fake, and avoid the prospect of falling for something that isnt real. But the attack method diffusion purification has already been able to nullify todays watermarks. Based on our results, designing a robust watermark is a challenging, but not necessarily impossible task, the paper said, offering a glimmer of hope. An effective method should possess specific attributes, including a substantial enough watermark perturbation, resistance to naive classification, and resilience to noise transferred from other watermarked images. More from TechRadar Pro These are the best AI tools we've come across What is generative AI and will it pave the way to AIOps? This is why in-house models are key to unlocking AI's potential ====================================================================== Link to news story: https://www.techradar.com/pro/we-broke-them-all-how-researchers-broke-current- image-watermarking-protections-and-what-it-means-for-a-new-era-of-truth-alteri ng-reality --- Mystic BBS v1.12 A47 (Linux/64) * Origin: tqwNet Technology News (1337:1/100) .