VERIMEDIA

International Workshop on Media Verification and Integrity

VERIMEDIA - IJCNN 2025 Workshop

This workshop in conjuction with IJCNN conference addresses the rising challenges of AI-generated content and deepfakes by exploring advancements in multimedia forensics, deepfake detection, adversarial machine learning, AI-generated media attribution, multimodal analysis. A key focus is lifelong media authentication, emphasizing AI's role in safeguarding media integrity by analyzing diverse media types—text, images, videos, and speech. The session highlights the critical importance of combating disinformation and ensuring trustworthy information across fields like forensics, fake news debunking, cyberattack mitigation, and politics. The primary objective is to bring together experts from these varied fields, policy makers and stakeholders to share challenges and solutions and foster collaborative discussions.

Call for Papers

Artificial Intelligence (AI) has profoundly impacted the creation, distribution, and consumption of digital media. However, it has also introduced significant challenges, such as the rise of deepfakes, AI-generated misinformation, and adversarial attacks. To address these pressing issues, this workshop will explore advancements in multimedia forensics, deepfake detection, adversarial machine learning, AI-generated media attribution, and multimodal analysis.

A primary focus will be on lifelong media authentication—a forward-looking approach to ensuring the integrity and trustworthiness of digital content. By analyzing diverse media types, including text, images, videos, and speech, we aim to address the critical need for reliable tools and techniques to safeguard against disinformation, support forensic investigations, mitigate cyberattacks, and uphold trust in digital communications.

This workshop is aimed at researchers from various fields, including computational intelligence (e.g., deep learning, machine learning), artificial intelligence (e.g., natural language processing, knowledge modeling, computer vision), social network analysis, and signal processing who are interested in applying their methods and techniques to the challenges of detecting and countering misinformation. Additionally, professionals, practitioners, and stakeholders active in fields like journalism, communication, fact-checking, and law enforcement will also find the discussions and outcomes of this workshop highly relevant.

We invite submissions on topics including, but not limited to:

Multimedia Forensics: Detection and attribution of manipulated content across various media types.
Deepfake Detection: Innovations in identifying AI-generated content.
Adversarial Machine Learning: Challenges and solutions in combating adversarial threats.
AI-Generated Media Attribution: Techniques for tracing and authenticating content origin.
Lifelong Media Authentication: Long-term strategies for maintaining media integrity.
Applications in Disinformation Detection: Case studies in forensics, fake news debunking, infodemic control, and politics.

Submission Guidelines: We welcome research papers, case studies, and position papers. Submissions should be original and not under review elsewhere. Manuscripts must follow the IJCNN rules here and should not exceed 8 pages. During the submission, authors should select as the subject area the name of the selected Workshop.

Important dates

Key deadlines and milestones for submission and participation

Workshop Papers Submission Deadline	March 27, 2025
Workshop Paper Acceptance Notification	April 15, 2025
Workshop Date	July 3, 2025

Submission

The VERIMEDIA workshop 2025 is organized as part of the workshop series at the International Joint Conference on Neural Networks (IJCNN 2025). Participation in the workshop is included for all registered conference attendees. We kindly remind authors that at least one representative for each accepted submission must register and be present at the workshop to deliver the presentation. Authors should select as the subject area the name of the selected Workshop.

Submit your paper

Demo Proposal

Private companies and public/academic institutions willing to show their potential in terms of products, demos and proof-of-concepts related to the workshop's topics can submit expressions of interest for the demo session. To participate it is necessary to register to the conference for at least one day (3rd july). Please fill in the form describing your proposal; we will soon contact you. For further info, please ask Gian Luca Marcialis (marcialis@unica.it). VERIMEDIA is hosted by Int. Joint Conf. on Neural Networks 2025 - July, 3rd, 2025 - Supported by SERICS consortium - https://sites.unica.it/ff4all/verimediaijcnn/

Keynotes

Distinguished speakers sharing cutting-edge research in media verification and integrity

Prof Sébastien Marcel

IDIAP Research Center, Switzerland

From Face Recognition to Deception: 20 Years in Biometrics and Synthetic Media

Bio: Sébastien Marcel holds a Ph.D. in signal processing from Université de Rennes I (2000) and is a senior researcher at the Idiap Research Institute in Switzerland, where he leads a team focused on biometrics security, including face, speaker, and vein recognition, as well as anti-spoofing. He lectures at EPFL on statistical pattern recognition and has served in editorial roles for top IEEE journals. He was the principal investigator of major EU projects like MOBIO, TABULA RASA, and BEAT.

Abstract: As a field of research, Biometrics, encompasses many topics such as recognition (face, voice, fingerprint, iris or vascular), vulnerability assessment or attack prevention (spoofing, deepfakes or morphing). Since most of these technologies are now AI-driven (e.g. face recognition is powered by large deep neural networks) it opens new challenges and research avenues. In this talk, I will give an overview of my own research in the field over the last 20 years within the Biometrics Security & Privacy group. I will depict a journey devoted to deceive face recognition with the aim to mitigate security and privacy risks.

Martino Jerian

CEO and Founder, Amped Software

The use of AI on photo and video evidence: opportunities, challenges, and regulations

Bio: Martino Jerian is the CEO and Founder of Amped Software. He graduated in Electronic Engineering (summa cum laude) at the University of Trieste (Italy) with a thesis on forensic image processing and founded Amped Software in 2008. He has extensive software engineering experience designing and starting the development of Amped Software products. He taught as a contract professor in a few university courses related to investigations, forensics, and intelligence, has published several scientific papers related to image and video forensics, and has also worked as a forensic expert in major judiciary cases.

Abstract: In this session, we will discuss the potential, challenges, and concerns related to the use of Artificial Intelligence (AI) while working on photo and video evidence. We will suggest some high-level guidelines for use during criminal investigations, and we will present a few applicative examples, such as the enhancement of faces, the interpretation of low-quality license plates, and the detection of deepfakes. For these examples we will discuss the applicability in a judiciary context and possible safeguards to implement. Additionally, we will review key court cases and regulatory updates, such as the AI Act, to provide a legal perspective on AI’s evolving role in video forensics. This session will offer forensic practitioners, legal professionals, and researchers a balanced perspective on leveraging AI while upholding scientific and legal standards.