Multimedia content protection: from model-based to data-driven approaches

CVC Seminar

Abstract:

In this talk, Dr Andrew D. Bagdanov, Dr Massimo Iuliani, Dr Dasara Shullani, Dr Daniele Baracchi & Simone Magistri will present the results of the research activity on multimedia content security carried out at the Information Engineering Department (DINFO) at the University of Florence. First, we will give a short introduction to the three main approaches to the forensic analysis of images and videos (container-, content-, and physics-based), and we will describe some recent works on these topics. Then, we will show some real-world forensic cases where these methods can be applied. Finally, we will talk about challenges and opportunities arising from the application of machine learning to Data Hiding and Multimedia Forensics, and we will conclude the seminar by delving into a recent publication that investigates applications of Continual Learning to social network media source identification.

Short bio:

Massimo Iuliani is a postdoctoral researcher at the Multimedia Forensics Laboratory (FORLAB) in Florence, Italy. Daniele Baracchi and Dasara Shullani are postdoctoral researchers at the Communications and Signal Processing Laboratory in the Information Engineering Department (DINFO) of the University of Florence. Simone Magistri is a member of the Global Optimization Laboratory (GOL) and doctoral candidate in the PhD Program in Smart Computing of the Universities of Florence, Pisa, and Siena. Andrew D. Bagdanov is Associate Professor in the Department of Information Engineering at the University of Florence and Senior Researcher at the Media Integration and Communication Center (MICC).