PARTNERS

The creation-diffusion of fake multimedia content, whether entirely computer-synthesized or obtained by manipulating original content, can be considered a danger to many aspects of our society. The overall phenomenon has reached unprecedented levels, thanks to the availability of artificial intelligence tools dedicated to generating fake content almost indistinguishable from real ones in a relatively simple way. Fighting so-called deepfakes, videos, images and audio clips, generated with deep learning techniques, requires the development of appropriate countermeasures. The project aims to develop theoretical and practical tools to detect fake or counterfeited content, trace back to its origin, and limit its diffusion, through passive analysis techniques operating when the content is used or diffused, and active protection methods to be adopted at the time of content creation, to facilitate subsequent authentication.