Digital forensics and blockchain technology against deceptive deepfake images in social media
Manipulating an image or video is becoming easier and easier: “deepfakes”, i.e. the synthesis of the human image based on Artificial Intelligence, is a growing phenomenon today. Apart from a few examples of comedy or jokes, the scenarios opening up are alarming: scams, cyberbullying, revenge porn, and computer crimes. To fight the diffusion of those synthetically AI-generated images on social networks, TrueBees combines innovative AI digital image forensics methods with blockchain technology to guarantee that a given visual user-generated content is trustworthy.
A first prototype of the solution is publicly available on TrueBee’s official website.
Additional information can be found here:
- Interview (English subtitles available) with Giulia Boato on deepfakes: TrueBees: an EU-funded project to fight deep fakes on social network
- Article on U-Hopper’s blog: Seeing is believing… or maybe not
- Podcast Radio24 | Episode 1 (Italian only): Un algoritmo per sgamare i deepfake
- Podcast Radio24 | Episode 2 (Italian only): Falsi utenti della rete
Daniele Miorandi, project coordinator (U-Hopper)
Carlo Caprini, Tech lead – System design & integration (U-Hopper)
Davaadorj Battulga, Software Software Engineering (U-Hopper)
Giulia Boato, scientific manager (University of Trento)
Sebastiano Verde, AI Digital Forensics Training & Prototyping (University of Trento)
Antonio Luigi Stefani, Research and software development (University of Trento)
Diego Taglioni, Business development (U-Hopper)
Eleonora Aste, Communication Specialist (U-Hopper)
U-Hopper has shipped blockchain-enabled solutions to its customers since 2019. The team has working experience with both permissioned and permissionless blockchain frameworks. Applications developed by U-Hopper on blockchains include, e.g., a solution for managing the lifecycle of education certificates and a system for managing the informed consent provided by users to process their data. Further, U-Hopper has working experience with the configuration and deployment of blockchain nodes (particularly in Hyperledger Fabric), having deployed networks of up to 50 nodes.