Wednesday, September 25 at 2pm ET
Challenging Deepfakes: Detecting AI-generated Images With Geometrical Analysis and Deep Learning
Once upon a time, we used to say: "Seeing is believing". Nowadays, deepfakes have become a serious challenge to the credibility of visual content. They are being weaponized in all possible ways, from generating non-consensual pornography to fostering misinformation and political distrust. AI-synthesized images are especially dangerous since generating them requires limited skills and affordable tools. While there is no silver-bullet algorithm for detecting this kind of deepfakes, combining several types of analysis increases the chances of success.
In this webinar, we'll see how Amped Authenticate, the leading software for image and video authentication, empowers analysts' abilities to fight and win the deepfake challenge. We'll show how to detect inconsistencies in shadows and reflections, a common defect in AI-generated imagery, and how to use Authenticate's powerful deepfake detection classifiers that use AI to combat AI.
Webinar Presenter
Marco Fontani earned his MSc in Computer Engineering in 2010 at the University of Firenze (Italy) and his Ph.D. in Information Engineering in 2014 at the University of Siena (Italy), where his research focused on multimedia forensics. His PhD dissertation, "Digital Forensic Techniques for Splicing Detection in Multimedia Contents", was awarded the Best 2015 PhD Thesis on Signal Processing by the Italian National Telecommunications and Information Theory Group (GTTI).
He is currently the Forensic Director at Amped Software, a software company developing image and video forensic solutions for law enforcement agencies worldwide. He participated in several research projects funded by the EU and EOARD. He authored/co-authored over 30 journal and conference proceedings papers. He also has experience in delivering training to law enforcement, and he provided expert witness testimony on several forensic cases involving digital images and videos.
Marco is a former member of the IEEE Information Forensics and Security Technical Committee, and he actively contributed to the development of ENFSI’s Best Practice Manual for Image Authentication.
Marco Fontani
Forensics Director, Amped Software
