The most well-known line of inquiry in the growing anti-deepfake research sector involves systems that can recognize artifacts or other supposedly distinguishing characteristics of deepfaked, synthesized,...
Ironically, Stable Diffusion, the new AI image synthesis framework that has taken the world by storm, is neither stable nor really that ‘diffused’ – at least,...
The release of stability.ai’s Stable Diffusion latent diffusion image synthesis model a couple of weeks ago may be one of the most significant technological disclosures since...
Opinion When Generative Adversarial Networks (GANs) first demonstrated their capability to reproduce stunningly realistic 3D faces, the advent triggered a gold rush for the unmined potential...
Since the golden age of Roman statuary, depicting human hair has been a thorny challenge. The average human head contains 100,000 strands, has varying refractive indices...
Opinion Natural Language Generation models such as GPT-3 are prone to ‘hallucinate’ material that they present in the context of factual information. In an era that’s...
Yesterday’s debut of episode 6 of the Star Wars spin-off The Book of Boba Fett seems to have divided fan opinion. Received to general approbation, there’s...
Analysis For campaigners hoping that 2022 could be the year that deepfaked imagery falls within a stricter legal purview, the early indicators are unpromising. Last Thursday...
Attacking image recognition systems with carefully-crafted adversarial images has been considered an amusing but trivial proof-of-concept over the last five years. However, new research from Australia...
CGI data augmentation is being used in a new project to gain greater control over deepfake imagery. Though you still can’t effectively use CGI heads to...
This morning, trawling the Computer Science sections of Arxiv, as I do most mornings, I came across a recent paper from the Federal University of Ceara...
