DESCRIPTION
The spread of disinformation has become a growing concern, with AI playing a dual role as both a tool for creating and combating false information. The rapid advancement of AI technologies has enabled the generation of highly convincing manipulated media, making it increasingly difficult for individuals and platforms to distinguish between truth and falsehood. As this challenge grows, it becomes essential to explore the complex intersection between AI and disinformation.
This session consists of four talks addressing both the conceptual and technical aspects of AI’s role in disinformation.
- Key definitions and challenges, impact, and real-world examples of various types of disinformation including AI-driven disinformation. It will also cover the behavioral, economic, and political factors that drive the spread of disinformation, as well as potential solutions through technical tools, education, policy-making, and regulations. (I. Kompatsiaris)
- Synthetic media generation and detection, including the tasks of image manipulation detection and localization, synthetic image detection, deepfake detection, and the associated challenges in porting solutions to the hands of journalists and fact checkers (S. Papadopoulos, CERTH-ITI)
- Combatting video-borne disinformation: extraction of keyframes for detecting video re-use on the web; extraction and visual enhancement of contextual cues (e.g. text regions) for detecting out-of-context videos. Increasing trust in AI methods for combatting disinformation: AI explainability techniques for image deepfake detectors. (Vasileios Mezaris)
- Fundamental concepts of multimodal deep learning for disinformation detection, including data preprocessing techniques, custom data loaders, neural network design and model training using Python and PyTorch. Participants will be called to implement and train deep learning models capable of detecting multimodal types of misinformation, namely out-of-context images and (Stefanos Iordanis Papadopoulos).
DETAILS
Couse type: Special session
Duration: 3 lectures – 30’-45’ each, 1 hands-on session approx. 1:30-2 hours
Institution of lecturers: CERTH – ITI (Centre for Research and Technology Hellas – Information Technologies Institute)
LECTURERS
Dr. Ioannis (Yiannis) Kompatsiaris (organizer of the special session) is the Director of CERTH-ITI and the Head of Multimedia Knowledge and Social Media Analytics Laboratory. His research interests include ΑΙ/ML for multimedia, Semantics, Social Media and Big Data Analytics, Multimodal and Sensors Data Analysis, Brain Computer Interfaces, e- Health, Cultural, Media/Journalism and Security applications. He is the co-author of 222 papers in refereed journals, 69 book chapters, 10 patents and 641 papers in international conferences. Google Scholar reports an h-index=68. He has been the co-chair of various international conferences and has served as a regular reviewer, associate and guest editor for a number of journals and conferences. He is a member of the National Ethics and Technoethics Committee, the Scientific Advisory Board of the CHIST-ERA funding programme and has been an elected member of the IEEE IVMSP – TC. He is an ELLIS Fellow and a Senior Member of IEEE and ACM.
Dr. S. Papadopoulos is a Principal Researcher at the Information Technologies Institute, Centre for Research and Technology Hellas (CERTH-ITI), Thessaloniki, Greece. He holds a PhD degree in Computer Science from the Aristotle University of Thessaloniki (2012) on the topic of Knowledge discovery from large-scale mining of social media content. His research interests lie at the intersection of multimedia understanding, social network analysis, information retrieval, big data management and artificial intelligence. Dr. Papadopoulos has co-authored more than 50 papers in refereed journals, 10 book chapters and 140 papers in conferences, 3 patents/workshops, and has co-edited two books. He participates in and coordinates a number of relevant EC FP7, H2020 and HE projects in media convergence, social media and artificial intelligence. He is heading the Media Analysis, Verification and Retrieval Group (MeVer), and is a co-founder of the Infalia Private Company, a spin-out of CERTH-ITI.
Dr. Vasileios Mezaris is a Research Director at the Information Technologies Institute (ITI) of the Centre for Research and Technology Hellas (CERTH), and the Head of the Intelligent Digital Transformation Laboratory of CERTH-ITI. He received the B.Sc. and Ph.D. degrees in electrical and computer engineering from the Aristotle University of Thessaloniki, Greece, in 2001 and 2005, respectively. His research interests include multimedia understanding and artificial intelligence. He has co-authored more than 40 papers in refereed journals, 20 book chapters, 200 papers in international conferences, and 3 patents. He is a Senior Member of the IEEE.
S.-I. Papadopoulos is a Research Associate at the Information Technologies Institute (ITI) of the Centre for Research & Technology Hellas (CERTH). As a member of Media Analysis, Verification and Retrieval Group (MeVer), he has been involved in several EU-funded projects. His main research interests lie in the areas of multimodal deep learning, focusing on multimedia verification and retrieval, such as automated multimodal misinformation detection and fact-checking, where he has co-authored several conference and journal articles.