The credibility of digital media has been increasingly undermined in the last years by the availability of easy-to-use media editing tools and the development of AI-techniques, which enable even users with no to little technical skills to create visually plausible fake videos.
To goal of the PREMIER project is to devise a new class of techniques capable of distinguishing fake from original videos, with the objective of decreasing the amount of data needed for training forensic detectors, providing ways to interpret their results, and improving their security against strategic forgeries.
The developed tools are integrated into this demonstrator whereby users can assess the authenticity of a set of pre-loaded videos as well as their own videos.
Disclaimer 1! This demonstrator is the result of scientific activities within a research project. The techniques are trained and tested in controlled scenarios focused on face swaps data, and their performance on arbitrary deepfake data are not guaranteed. Intuitive result visualizations are displayed for dissemination purposes, expertise is required for an in-depth analysis and interpretation of the forensic outputs.
Warning! A fast connection is recommended for proper rendering of the interface.
Alessandro Piva is Associate Professor at the Department of Information Engineering of the University of Florence. He is also head of FORLAB – Multimedia Forensics Laboratory of the University of Florence. His research interests lie in the areas of Information Forensics and Security, and of Image and Video Processing. In the first topic, he was interested in data hiding, signal processing in the encrypted domain, image and video forensic techniques. In the second area, he was interested in the design of image and video processing and analysis techniques for Cultural Heritage, medical and industrial applications. In the above research topics he has been co-author of more than 50 papers published in international journals and 120 papers published in international conference proceedings. He holds 3 Italian patents and an International one on digital watermarking. He is IEEE Fellow, and he is member of the IEEE Information Forensics and Security Technical Committee.
Daniele Baracchi is a postdoctoral fellow at the University of Florence. He holds a bachelor and a master in Computer Engineering and a Ph.D. in Information Engineering from the University of Florence. Since 2018 he has been a member of the Image Analysis, Processing, and Protection Research Group of the Department of Information Engineering of the University of Florence, where he is developing machine learning-based methods for multimedia forensics. In the last four years he worked on research projects funded by the US Defence Advanced Research Project Agency (DARPA) and by the Italian Ministry of University and Research (MUR).
Post Graduate Master Degree in Applied Mathematics at University of Florence in December 2011 with the thesis "Optimization techniques for Universal Counter Forensics". Vote 110/110 cum laude.
He currently works in the Image Analysis Processing and Protection group within the Dept. of Information Engineering of the University of Florence.
In the last seven years he worked on research projects funded by the European Commission (EC) and by the US Defense Advanced Research Projects Agency (DARPA). All projects were related to authentication and reverse engineering of multimedia contents.
Technical Supervisor at FORLAB, the Multimedia Forensics Laboratory (www.forlab.org) at PIN s.c.r.l. Educational and Scientific Services for the University of Florence. His main activities involve the training of law enforcement and legal operators and the consultancy multimedia contents analysis (digital images, audio and videos) for forensic purposes.
Dasara Shullani is a postdoctoral fellow at the University of Florence. She holds a master in Computer Engineering from Politecnico di Torino and a Ph.D. in Information Engineering from the University of Florence. Since 2015 she has been a member of the Image Analysis, Processing, and Protection Research Group of the Department of Information Engineering of the University of Florence, where she is developing multimedia forensics tools applied to video contents. During this period she worked on research projects funded by the Consortium GARR, the US Defence Advanced Research Project Agency (DARPA) and by the Italian Ministry of University and Research (MUR).
Dr. Luisa Verdoliva is Associate Professor at University Federico II of Naples, Italy, where she leads the Multimedia Forensics Lab. In 2018 she has been visiting professor at Friedrich-Alexander-University (FAU) and in 2019-2020 she has been visiting scientist at Google AI in San Francisco. Her scientific interests are in the field of image and video processing, with main contributions in the area of multimedia forensics. She has published over 120 academic publications, including 45 journal papers. She has been the PI for University Federico II of Naples in the DISPARITY (Digital, Semantic and Physical Analysis of Media Integrity) project funded by DARPA under the MEDIFOR program (2016-2020), and she is the PI for the same University in the DISCOVER (a Data-driven Integrated Approach for Semantic Inconsistencies Verification) project funded by DARPA under the SEMAFOR program (2020-2024). She has actively contributed to the academic community through service as general co-Chair of the 2019 ACM Workshop on Information Hiding and Multimedia Security, technical Chair of the 2019 IEEE Workshop in Information Forensics and Security and area Chair of the IEEE International Conference on Image Processing since 2017. She is on the Editorial Board of IEEE Transactions on Information Forensics and Security and IEEE Signal Processing Letters. Dr. Verdoliva is Chair of the IEEE Information Forensics and Security Technical Committee. She is the recipient of the 2018 Google Faculty Award for Machine Perception and a TUM-IAS Hans Fischer Senior Fellowship (2020-2023). She has been elected to the grade of IEEE Fellow since January 2021.
Giovanni Poggi received the Laurea degree in Electronic Engineering from the University Federico II of Naples (UNINA) in July 1988. In 1990 he joined the Department of Electrical Engineering and Information Technology of the same University where, since, November 2002, he is full professor of Telecommunications. In 1992 he has been Visiting Scholar at the Information Systems Laboratory directed by prof. Robert Gray at Stanford University, USA. At UNINA he has been Chair of the PhD program in Electronic and Telecommunication Engineering (2005-2009) and Chair of the Bachelor/Master Program in Telecommunication Engineering (2009-2017). From 2019 to 2021 he has been President of the Commission for the National Scientific Habilitation in Telecommunications.
His research interests concern the processing of digital images and videos (description, retrieval, compression, segmentation, classification, restoration, fusion, source identification, liveness detection, object detection and localization) with main applications in remote sensing and digital image forensics. To guarantee reproducible research, the code of most proposed algorithms is published on-line (www.grip.unina.it). Giovanni heads the Image Processing Research Group (GRIP) at University Federico II of Naples, which currently includes two professors, Luisa Verdoliva and Giuseppe Scarpa, three post-Docs, and four PhD students. He has been local coordinator for several PRIN projects, has been co-PI of the DISPARITY program (2016-2020) funded by DARPA and is co-PI of the DISCOVER program (2020-2024) funded by DARPA, both on multimedia forensics. He has been the supervisor of 15 PhD students. He has published more than 50 journal and 100 conference papers which received almost 6000 citations (https://scholar.google.it/citations?user=Xe_T0N0AAAAJ&hl=it) with an h-index of 39.
Davide Cozzolino received the Laurea degree in computer engineering and the Ph.D. degree in information engineering from the University Federico II of Naples, Naples, Italy, in 2011 and 2015, respectively. He is currently an Assistant Professor at the Department of Electrical Engineering and Information Technologies, University of Naples. He has been assistant for the courses of Multimedia Signal Processing and Vision for Robotic Systems. His research interests include image processing and deep learning, with applications to remote sensing (image analysis and restoration) and multimedia forensics (image forgery detection and localization). His relevant contributes was on the definition of blind approaches for manipulation localization and the design of an efficient copy-move forgery detection method both for images and videos. He participated in different international challenges on multimedia forensics, his team won the 2013 IEEE Image Forensics Challenge and the 2018 IEEE Signal Processing Cup.
Mauro Barni graduated in electronic engineering at the University of Florence in 1991. He received the PhD in informatics and telecommunications in October 1995. During the last two decades he has been studying the application of image processing techniques to copyright protection and authentication of multimedia, and the possibility of processing signals that have been previously encrypted without decrypting them. Lately he has been working on theoretical and practical aspects of adversarial signal processing with a particular focus on adversarial multimedia forensics.
He is author/co-author of about 350 papers published in international journals and conference proceedings, and holds five patents in the field of digital watermarking and image authentication. He is co-author of the book âWatermarking Systems Engineering: Enabling Digital Assets Security and other Applicationsâ, published by Dekker Inc. in February 2004.
He participated to several National and International research projects on diverse topics, including computer vision, multimedia signal processing, remote sensing, digital watermarking, multimedia forensics.
He has been the Editor in Chief of the IEEE Transactions on Information Forensics and Security for the years 2015-2017. He was the funding editor of the EURASIP Journal on Information Security. He has been serving as associate editor of many journals including several IEEE Transactions. Prof. Barni has been the chairman of the IEEE Information Forensic and Security Technical Committee (IFS-TC) from 2010 to 2011. He was the technical program chair of ICASSP 2014. He was appointed DL of the IEEE SPS for the years 2013-2014. He is the recipient of the Individual Technical Achievement Award of EURASIP for 2016. He is a fellow member of the IEEE and a member of EURASIP.
Benedetta Tondi received the master degree (cum laude) in Electronics and Communications Engineering at the University of Siena in 2012 and her PhD degree in Information Engineering and Mathematical Sciences at the University of Siena in 2016, with a thesis on the Theoretical Foundations of Adversarial Detection and Applications to Multimedia Forensics, in the area of Multimedia Security.
She is currently an Assistant Professor at the Department of Information Engineering and Mathematics, University of Siena. She has been assistant for the course of Information Theory and Coding and Multimedia Security. She is a member of the Visual Information Processing and Protection (VIPP) Group led by Prof. Mauro Barni. She is part of the IEEE Young Professionals and IEEE Signal Processing Society, and a member of the National Inter-University Consortium for Telecommunications (CNIT). From January 2019, she is Elected Member of the Information Forensics and Security (IFS) Technical Committee of the IEEE Signal Processing Society.
Her research interest focuses on the application of Information-Theoretic methods and Game theory concepts to Forensics and Counter-Forensics analysis and more in general to Multimedia Security, and on Adversarial Signal Processing. Recently, she is working on Machine Learning and Deep Learning applications for Digital Forensics and Counter-Forensics, and on the security of Machine Learning techniques.
From October 2014 to February 2015 she has been a visiting student at the University of Vigo at the Signal Processing in Communications Group (GPSC), working on the study of techniques to reveal attacks in Watermarking Systems. Her stay was funded by a Spanish National Project on Multimedia Security.
She is recipient of the Best Student Paper Award at the IEEE International Workshop on Information Forensics and Security (WIFS) 2014, the Best Paper Award at the IEEE International Workshop on Information Forensics and Security (WIFS) 2015 and at the The Ninth International Conferences on Advances in Multimedia (MMEDIA) 2017. She is winner of the 2017 GTTI PhD Award for the best PhD Theses defended at an Italian University in the areas of Communications Technologies (Signal Processing, Digital Communications, Networking).
Giulia Boato was born in Rovereto (Trento) in 1979. In 2002 she received the M.Sc. degree in Mathematics at the Faculty of Science of the University of Trento. In 2005 she obtained the Ph.D. in Information and Communication Technologies, working in the Multimedial Signal Processing and Understanding Lab on innovative methodologies for secure multimedia communications using Birkhoff polynomial interpolation. Currently, she is Assistant Professor at the Department of Information Engineerig and Computer Science (DISI) of the University of Trento (Italy) and professor of the courses Digital signal processing and Data hiding within the M.Sc. Degree in Telecommunications Engineering. From 2008 to 2011 she has been coordinating the Multimedial Signal Processing and Understanding Lab. She was in the Project staff of some past projects (DIPLODOC, AIDER, GRID.IT, PERSEO) and on-going projects (EU projects: SAFESPOT, FP7 FET-IP LIVINGKNOWLEDGE, FP7 IP GLOCAL, FP7 CA ETERNALS). She is co-chair of the International Workshop Living Web: making diversity a true asset (Washington DC, October 2009) within the International Semantic Web Conference 2009 and of the workshop on Event-based Media Integration and Processing co-located with ACM Multimedia conference 2013. She is in the Technical Program Committee of the International Conference on Image Processing (ICIP) and of the International Conference on Communications (ICC); and Local Arrangements Chair of the International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks 2005 and of the International Conference on Multimedia Retrieval 2011. She is reviewer for many international journals, e.g., IEEE Transaction on Information Forensics and Security, IEEE Transaction on Signal Porcessing, IEEE Transaction on Multimedia, IEEE Transaction on Circuits and Systems for Video Technology. In 2006 she was visiting researcher at the Signal Theory and Communications Department of the University of Vigo (Spain). Since 2006 she has been collaborating with the Signal Processing Department of the Tampere University of Technology (Finland), in particular with prof. Karen Egiazarian. Since 2009 she has been working with prof. Hany Farid of the Dartmouth College (USA) on digital image and video forensics techniques, co-advising a Ph.D. thesis. In 2012 she was visiting researcher at the Multimedia Information Retrieval Lab of the University of Delft (the Netherlands). Her research interests are focused on image and signal processing, with particular attention to multimedia data protection, data hiding and image forensics, but also intelligent multidmensional data management and analysis. On these topics she is active in the european prjects coordinated by DISI: in LIVINGKNOWLEDGE for the development of image forensics methods supporting opinion mining on the web, in GLOCAL for the desing of multimedia annotation and retrieval systems based on the concept of event.
Cecilia Pasquini received her PhD in 2016 from the ICT International Doctoral School of the University of Trento, Italy, for the thesis "Statistical and deterministic approaches for multimedia forensics". From 2016 to 2020, she has been a Postdoctoral Fellow at the Privacy and Security Lab with the Universität Innsbruck, Austria, and at the IT Security Lab at the University of Münster, Germany. In 2013, she was visiting PhD student at the University of Vigo, Spain. Prior to that, she received a BS and MS degree in Mathematics from the University of Ferrara, Italy, in 2010 and 2012.
Her research area lies at the intersection of multimedia signal processing and information security, with special focus on image and video forensics, multimedia security, adversarial signal processing and machine learning. She has participated in several projects on these topics, such as PREMIER (funded by MIUR), ITBDIF (funded by Deutsche Forschungsgemeinschaft), J-MDS, NOTIS, ECMSF (funded by EUREGIO).
She has been General Co-Chair of the ACM Workshop on Information Hiding & Multimedia Security 2018, and co-organizer of the special session "Information Security meets Adversarial Examples" at IEEE WIFS 2019. She is member of the Technical Program Committe of several conferences and workshops (e.g., ACM IH&MMSec, IEEE WIFS, IEEE ICASSP, EUSIPCO), and serves as reviewer for many journals (e.g., IEEE TIFS, IEEE TCSVT, IEEE TIP, EURASIP JIS). She is an elected member of the Eurasip BForSec Technical Area Committee. She received the Top 10% paper award (IEEE International Workshop on Multimedia Signal Processing 2013) and the “F. Carassa” GTTI 2015 award for the best ongoing PhD.
Federica Lago is a PhD candidate of the IECS Doctoral School in Trento. She received her M.Sc. in Computer Science in 2017, and she worked as a research fellow in the MMLab group before starting her PhD in 2018. Her main research interests are connected with multimedia forensics and data analysis. Her research is currently focused on the recognition of the provenance of images that are shared online and the possible impact they can have on people.
Andrea Montibeller received his M.Sc. in Information and Communications Engineering in 2020. He was research fellow at the University of Vigo for 6 month during 2018, working for prof. Fernando Pérez-González and since November 2020 he is a PhD student with the ICT Doctoral School. His main research interests focused on multimedia forensics are: source identification of videos based on the use of noise residuals and recognizing video fully or partially generated by GANs.
Stefano Tubaro completed his studies in Electronic Engineering at the Politecnico di Milano, Milan, Italy, in 1982.
He then joined the Dipartimento di Elettronica, Informazione e Bioingegneria of the Politecnico di Milano, first as a Researcher of the National Research Council, and then (in November 1991) as an Associate Professor.
Since December 2004, he has been appointed as a Full Professor of telecommunication at the Politecnico di Milano.
His current research interests include advanced algorithms for video and sound processing.
He is the author of more than 180 scientific publications on international journals and congresses and the coauthor of more than 15 patents.
In the past few years, he has focused his interest on the development of innovative techniques for image and video tampering detection and, in general, for the blind recovery of the ``processing history'' of multimedia objects.
He coordinates the research activities of the Image and Sound Processing Group at the Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano.
He had the role of Project Coordinator of the European Project ORIGAMI (A new paradigm for high-quality mixing of real and virtual) and of the research project ICT-FET-OPEN REWIND (REVerse engineering of audio-VIsual coNtent Data).
This last project was aimed at synergistically combining principles of signal processing, machine learning, and information theory to answer relevant questions on the past history of such objects.
He is a member the IEEE Multimedia Signal Processing Technical Committee and of the IEEE SPS Image Video and Multidimensional Signal Technical Committee.
He was in the organization committee of a number of international conferences including the IEEE MMSP 2004/2013, IEEE ICIP 2005, IEEE AVSS 2005/2009, IEEE ICDSC 2009, IEEE MMSP 2013, IEEE ICME 2015.
From May 2012 to April 2015, he was an Associate Editor of the IEEE TRANSACTIONS ON IMAGE PROCESSING, and is currently an Associate Editor of the IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY.
Paolo Bestagini received the M.Sc. degree in Telecommunications Engineering and the Ph.D. degree in Information Technology from the Politecnico di Milano, Italy, in 2010 and 2014, respectively.
He is currently an Assistant Professor at the Image and Sound Processing Lab (ISPL), Politecnico di Milano.
His research interests focus on multimedia forensics and acoustic signal processing for microphone arrays.
He is Associate Editor for the IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) and the Elsevier Journal of Visual Communication and Image Representation (JVCI).
He is elected member of the IEEE Information Forensics and Security Technical Committee, and a co-organizer of the IEEE Signal Processing Cup 2018.
Edoardo Daniele Cannas received his bachelor degree in Electrical and Electronic Engineering in 2016 from Università degli studi di Cagliari. He then obtained a M.Sc. in Computer Science and Engineering from Politecnico di Milano in 2019, following the Musical Acoustics track. From 2019 he joined the Image and Sound Processing Lab (ISPL) as a research assistant, while from 2020 he is pursuing a PhD in Information Technology. His main research interests focus on signal processing for multimedia forensics applications.