ICIP2026 - WORKSHOP

13-17 September 2026, Tampere, Finland

VICE CHANCELLOR

Main Topics:Quality-to-Confidence ModelingCalibrated UncertaintyMulti-Source Evidence FusionOperational RobustnessReliability-Centric Evaluation . .

BEYOND DETECTION: UNCERTAINTY, QUALITY, AND MULTI-SOURCE REASONING FOR OPERATIONAL MULTIMEDIA FORENSICS

ABSTRACT

This workshop addresses the critical transition from binary classification to decision-grade forensic architectures. This direction is supported by emerging research suggesting that forensic models, despite strong benchmarks, may degrade under domain shift and overfit to generator-specific artifacts, reducing real-world reliability. By treating forensic significance as a function of signal integrity, accounting for sensor noise, motion blur, and transcoding artifacts, and cross-source consistency, we bridge the gap between the IEEE Signal Processing Society and the Reliability and Information Fusion communities. The program targets five research pillars: Quality-to-Confidence Modeling (with dynamic evidence weighting and dataset shift), Calibrated Uncertainty (utilizing conformal prediction and proper scoring rules), Multi-Source Evidence Fusion (using evidence graphs), Operational Robustness, and Reliability-Centric Evaluation. While ICIP 2025 focused on detection, this workshop targets the operational reliability and legal defensibility of forensic signals. By shifting from binary "if" to calibrated "how much" a detection can be trusted, we provide a technical focus that complements ICIP 2026 tracks on Image Quality, Fusion, and Privacy. The proposal is informed by the organizers’ decade of experience in forensic projects and operational platforms with the Czech Police and European LEAs such as the Police Service of Northern Ireland and the Generalitat de Catalunya. By convening a TPC with strong ties to the EURASIP and IEEE ecosystems, we enable dialogue between theoreticians and practitioners. This synergy shifts attention from aggregate accuracy to statistical calibration, proper scoring rules, and high-TRL innovations that keep forensic signals technically robust and legally defensible.

COMPOSITION

The workshop is structured as a high-impact half-day event. The program opens with a 30-minute keynote, Decision-Grade Forensic Evidence: Technical and Operational Requirements. This is followed by two focused one-hour Technical Talk Sessions on Robustness Under Real-World Degradation & Dynamic Weighting of Localized Evidence and Uncertainty Quantification & Conformal Prediction for Forensic Reasoning, each featuring 3 oral presentations. The program concludes with a centralized Poster and Software Demo Session, where researchers present peer-reviewed posters alongside live demonstrations. This interactive core is designed to facilitate a direct feedback loop between academics and the broader investigative software community. To ensure diversity and ethical integrity, the committee will prioritize a balance of academic and real world perspectives and career diversity by reserving speaking slots for early-career researchers. We will prioritize detection transparency and responsible disclosure over methods that could serve as guides for forensic evasion. The proposed format ensures over five in-person presenters by combining six accepted papers with invited talk and a dedicated poster & demo session, effectively safeguarding against the conference's cancellation policy. The workshop maintains a high density of expertise and guaranteed operational stability for the ICIP 2026 program.

IMPORTANT DATES

Workshop Date: September 13 or 17, 2026
Duration: half day
Paper Selection Period: May – June 2026

ATTENDEES

30–40. The target audience includes academic researchers in signal processing and computer vision, reliability engineers, and platform integrity professionals, alongside practitioners from the content authenticity community and the specialized sector of investigative software development.

WORKSHOP PROCEEDINGS

Submit for publication in IEEE Xplore ICIP 2026 Workshop Proceedings. We will run a rigorous peer-review process with at least two expert reviews per paper and transparent conflict-of-interest handling, aligned with ICIP standards, and we aim for inclusion in the ICIP 2026 Workshop Proceedings on IEEE Xplore.

Proposal submitted

The workshop proposal has been submitted, and we are currently awaiting confirmation on whether it will be selected.

TECHNICAL PROGRAM COMMITTEE (TPC)

Alt Text

Associate Professor
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 60 papers published in international journals and 120 papers published in international conference proceedings, with h-index 43 according to Scopus. He is IEEE Fellow.

Learn More
Alt Text

Professor
FERNANDO PÉREZ GONZÁLEZ

received a Ph.D. in Telecommunications from the University of Vigo in 1993 and has been a Full Professor at the Department of Signal Theory and Communications since 2000, coordinating the GPSC research group since 1995. From 2009 to 2011, he held the Prince of Asturias Chair at the University of New Mexico and served as Manager of the National Research Plan between 2007 and 2010. He was the promoter and first Managing Director of Gradiant (2007–2014) and founded seven ICT companies, whose surviving firms employ around 150 engineers. He is the author of 65 international journal articles and over 170 conference papers, and has supervised 10 Ph.D. theses. He holds 14 patents, has led numerous European and industrial projects, and has been an IEEE Fellow

Learn More
Alt Text

Associate Professor
GIULIA BOATO

is an Associate Professor at the University of Trento, where she conducts research in multimedia signal processing and multimedia forensics. Giulia Boato received her Ph.D. in Information and Communication Technologies and has held research and academic positions both in Italy and abroad. Her research interests include multimedia security, image and video forensics, quality assessment, and analysis of visual data, with applications spanning security and digital media authenticity. She has authored numerous peer-reviewed journal and conference publications and is actively involved in international research collaborations and projects.

Learn More
Alt Text

Associate Professor
IRENE AMERINI

is an Associate Professor at Sapienza University of Rome, where she leads the Computer Vision and Multimedia Forensics Research Team at ALCORLab. Irene Amerini received her Ph.D. in Computer Engineering from the University of Florence with a thesis on image forensics, source identification, and tampering detection. She previously held research positions at Sapienza University of Rome and the University of Florence and was a Visiting Research Fellow at Charles Sturt University, Australia. Her research interests include computer vision, adversarial machine learning, and multimedia forensics, and she is actively involved in IEEE, EURASIP, and IAPR technical committees.

Learn More
Alt Text

Professor
CHRISTIAN RIESS

received his Ph.D. in Computer Science from Friedrich-Alexander University Erlangen-Nürnberg in 2012 and completed his habilitation in 2020. He is a senior researcher and head of the Multimedia Security Group at FAU, and currently serves as interim Professor of Applied Cryptography. His research focuses on image and video forensics, machine learning security, and robust image analysis, with strong emphasis on trustworthy and secure AI systems. He has authored a large body of high-impact journal and conference publications and has received over 11,000 citations. His work has been recognized by multiple best paper and reviewer awards, and he is an active contributor to the international multimedia forensics community.

Learn More
Alt Text

Associate Professor
ADAM CZAJKA

received his Ph.D. in Biometrics from the Warsaw University of Technology in 2005 and his habilitation in Computer Science in 2018. He is a tenured Associate Professor at the University of Notre Dame, where he also serves as the founding Director of the AI Trust and Reliability Lab (AITAR). His research focuses on biometrics and trustworthy AI, with particular emphasis on iris recognition, presentation attack detection, and human–machine teaming. He has authored numerous high-impact journal and conference publications, supervised multiple Ph.D. students, and holds several granted and pending U.S. patents. He is the recipient of an NSF CAREER Award and an active member of IEEE and the international biometrics research community.

Learn More
Alt Text

Professor
EMUS OVIDIU BRAD

is a Full Professor at Lucian Blaga University of Sibiu, where he is affiliated with the Department of Computer Science and Electrical Engineering. Remus Ovidiu Brad received his Ph.D. in Computer Science from the Technical University of Cluj-Napoca, with research focused on image processing and motion detection, and completed his habilitation in Computer Science and Engineering in 2015. He has held academic positions at ULBS since 1993 and has also served for many years as Director of the University’s IT and Communications Directorate. His research interests include image processing and computer vision, artificial intelligence, computer networks, and embedded systems, with strong engagement in doctoral supervision and academic leadership.

Learn More
Alt Text

Postdoctoral Researcher
HANNES MAREEN

is a Postdoctoral Researcher at IDLab-MEDIA, where he conducts research in multimedia security and forensics. He obtained his Ph.D. between 2017 and 2021 with financial support from the Research Foundation – Flanders (FWO). His doctoral research focused on video watermarking for tracing digital piracy, alongside work on image and video forgery detection, fingerprinting, and perceptual hashing. His broader expertise includes optical character recognition, dense captioning, low-delay live streaming, and medical image analysis. He is also active in science communication for non-experts and has received several awards, including the Agoriaprijs, two Best Poster Awards, the #ThesisThread competition prize, and a bronze trophy in the Vlaamse PhD Cup.

Learn More
Alt Text

Police of the Czech Republic
JAN HOŘÍNEK

is an Analytics & Information Coordinator at the Police of the Czech Republic, where he focuses on the use of data analytics to support operational and investigative decision-making. He participated in international collaborative projects such as the EU Horizon 2020 ROXANNE and the RELIEF, supporting the application of analytics in law enforcement practice. In 2002, he received an Ing. (M.Sc.) degree in Telecommunications and Radiotechnology from the Faculty of Electrical Engineering, Czech Technical University in Prague. His work bridges advanced analytical methods with real-world policing needs, contributing to evidence-based and data-driven security solutions.

Learn More

ORGANIZERS

Alt Text

Associate Professor
BARBARA ZITOVÁ

is a senior researcher and has led the Department of Image Processing at the UTIA institute since 2008, serving also as an associate professor at Charles University and the Czech Technical University in Prague. Her research in digital image processing and AI focuses on data fusion, object detection, and deep learning, with high-impact applications in forensic imaging. Bringing deep operational expertise to the workshop, she has been instrumental in three major national forensic projects involving universities, academic institutions and SMEs, leading the last one as principal investigator, all executed in direct cooperation with the Czech Police. Furthermore, she serves as an official expert for the European Union, evaluating high-level research projects in forensics and security application area.

Learn More
Alt Text

Senior Researcher
BABAK MAHDIAN

received his Ph.D. from the Czech Technical University in Prague, Czech Republic, in 2008. Since then, he has been a researcher in the Department of Image Processing at UTIA, where he has built an international reputation for his contributions to image forensics and machine learning. He is an award-winning scientist with extensive experience spanning both academic and commercial projects. His research focuses on image forensics, visual search, and small-data supervised learning, and he has served as principal investigator on several national as well as EU H2020 and Horizon projects, including initiatives such as VIGILANT, aimed at visual content verification and combating disinformation.

Learn More
Alt Text

Research Fellow
ADAM NOVOZÁMSKÝ

is a research fellow and deputy head of the Department of Image Processing at the Institute of Information Theory and Automation (UTIA), The Czech Academy of Sciences, where he develops applied computer vision and machine learning methods for forensic, industrial, and medical imaging. His research focuses on image forensics and robust visual analysis, including the detection of manipulated imagery and automated object and human detection and tracking. He has international experience from a postdoctoral appointment at TU Wien and has contributed to several competitive national and EU projects in multimedia verification and related security applications. In addition, he leads practical exercise sessions in machine learning and digital image processing at Czech Technical University and Charles University.

Learn More

Search