Mathematics Webinar | Benford's Law in the Age of AI: New Frontiers in Data Authenticity and Model Transparency
the chair
20th Mathematics Webinar
Benford's Law in the Age of AI: New Frontiers in Data Authenticity and Model Transparency
As artificial intelligence (AI) systems increasingly shape critical decisions in finance, auditing, cybersecurity, and governance, the demand for interpretable, transparent, and data-authentic models continues to grow. In this context, Benford’s Law—a mathematical law that predicts the frequency distribution of leading digits in naturally occurring datasets—emerges as a valuable tool for anomaly detection, model validation, and forensic analysis.
This webinar explores the evolving role of Benford’s Law in the age of AI, emphasizing how it can be integrated into machine learning workflows as a statistical feature for identifying irregularities and improving model accountability. By embedding digit-based conformity tests into AI pipelines, analysts and developers can enhance the explainability of models and proactively detect data manipulation, bias, or fraud in large-scale systems.
One of the focuses of the session will be the statistical analysis of how Pareto and Weibull distributions, frequently used in economics, risk modeling, and reliability engineering, align with Benford’s expected digit frequencies. We will discuss both the theoretical underpinnings and present empirical evidence to evaluate the extent to which these distributions comply with Benford’s Law, and what that means for AI systems trained on such data.
Participants will gain insights into cutting-edge applications, including hybrid AI models that combine traditional statistical methods with deep learning, as well as the use of Benford-based metrics in improving robustness, reducing false positives, and enhancing the interpretability of black-box models.
Whether you are a researcher, auditor, data scientist, or AI practitioner, this webinar will offer a multidisciplinary perspective on how mathematical laws, statistical rigor, and artificial intelligence can work together to build more trustworthy and resilient systems.
Date: 29 September 2025
Time: 12:00 PM CEST
Webinar ID: 865 9326 5734
Webinar Secretariat: journal.webinar@mdpi.com
Meet the Event Chair
Meet Our Speakers
Dr. Dragan Azdejkovic
Department of Statistics and Mathematics, University of Belgrade, Faculty of Economics and Business, 11000 Belgrade, Serbia;
Dragan Azdejković is an associate professor at the University of Belgrade – Faculty of Economics and Business (Department of Statistics and Mathematics). He graduated from the Faculty of Mathematics, University of Belgrade (module: Numeric Mathematic and optimisation). He received his master's degree at the Faculty of Mathematics, University of Belgrade (module: Optimisation). He obtained PhD in Operational Research at the Faculty of Economics and Business, University of Belgrade. Dragan Azdejković has been employed at the Faculty of Economics and Business, University of Belgrade since 1990. His research mainly focuses on Operational Research, Game Theory, Social Choic and applied Statistics. He is a member of the next societies: Mathematical Society of Serbia; Council of the Faculty of Economics and Business; Scientific Society of Economists.
Dr. Jelena Stanojevic
Department of Statistics and Mathematics, University of Belgrade, Faculty of Economics and Business, Belgrade, Serbia;
Jelena Stanojević is an associate professor at the University of Belgrade – Faculty of Economics and Business (Department of Statistics and Mathematics). She graduated from the Faculty of Mathematics, University of Belgrade (module: Probability and Statistics). She received her master's degree at the Faculty of Mathematics, University of Belgrade (module: Probability and Statistics). She obtained PhD in Mathematics (Area: Probability and Statistics) at the Faculty of Mathematics, University of Belgrade. Jelena Stanojević has been employed at the Faculty of Economics and Business, University of Belgrade since 2003. She was also employed at the private company Informatika, in the position of programmer. Her research mainly focuses on applied mathematics, computational, and theoretical statistics as well as risk theory. She is a member of the Mathematical Society of Serbia.
Prof. Dr. Tatjana Rakonjac-Antić
Department of Economic Policy and Development, University of Belgrade, Faculty of Economics and Business, Belgrade, Serbia;
Tatjana Rakonjac-Antić is a Full Professor at the Faculty of Economics and Business, University of Belgrade. She teaches undergraduate courses Insurance and Pension and Health Insurance, and master courses Insurance Analysis and Pension and Health Insurance Analysis. From the beginning of her work at the Faculty of Economics until today, Tatjana Rakonjac-Antić has had a large number of papers in scientific journals and proceedings published. Moreover, Tatjana Rakonjac-Antić has been engaged in numerous projects and participated in many domestic and international conferences. She is a member of the Scientific Society of Economists of Serbia and the Serbian Actuarial Association.
Dr. Dragana Radojicic
Department of Statistics and Mathematics, University of Belgrade, Faculty of Economics and Business, Belgrade, Serbia;
Dragana Radojičić is an assistant professor at the University of Belgrade – Faculty of Economics and Business (Department of Statistics and Mathematics). She graduated from the Faculty of Mathematics, University of Belgrade (module: Statistics, Actuarial and Financial Mathematics). She received her master's degree at the Faculty of Mathematics, Technical University of Berlin (module: Stochastic Processes). She obtained PhD in Mathematics at the Faculty of Mathematics and Geoinformation, Vienna University of Technology, where she had been working from 2016 until 2020 as a Teaching Assistant at the Department for Financial and Actuarial Mathematics. Since November 2021 she has been employed as an Assistant professor at the Faculty of Economics and Business, University of Belgrade. Her research mainly focuses on applied, computational, and theoretical probability and statistics, as well as machine learning. She is a member of the next societies: Mathematical Society of Serbia; Heidelberg Laureate Forum alumni club.
Sponsors and Partners
Organizer
On Monday, 29 September 2025, MDPI and the Journal Mathematics organized the 20th webinar on Mathematics, entitled "Benford's Law in the Age of AI: New Frontiers in Data Authenticity and Model Transparency".
The introduction was held by the Chair, Prof. dr Vesna Rajić. She has been a Full Professor at the University of Belgrade – Faculty of Economics and Business (Department of Statistics and Mathematics) since 2017. She obtained a PhD in Statistics in 2007 at the University of Belgrade. Her research mainly focuses on theoretical statistics as well as nonlinear analysis and actuarial mathematics.
The first speaker was Dr Dragan Azdejković, who presented "Benford’s Law in Electoral Forensics: Applications, Challenges, and Constraints". He has been an Associate Professor at the University of Belgrade – Faculty of Economics and Business (Department of Statistics and Mathematics). He obtained a PhD in Operational Research at the University of Belgrade. His research mainly focuses on operational research, game theory, social choic and applied statistics.
The second presentation, titled "Statistical analysis of fitting Pareto and Weibull distributions with Benford’s Law: theoretical approach and empirical evidence", was held by Prof. Dr Tatjana Rakonjac Antić and Dr Jelena Stanojević. Tatjana Rakonjac-Antić is a Full Professor at the Faculty of Economics and Business, University of Belgrade. She teaches undergraduate courses on Insurance and Pension and Health Insurance and master’s degree courses on Insurance Analysis and Pension and Health Insurance Analysis. Jelena Stanojević is an Associate Professor at the University of Belgrade – Faculty of Economics and Business (Department of Statistics and Mathematics). She obtained a PhD in Mathematics (Area: Probability and Statistics) at the University of Belgrade. Her research mainly focuses on applied mathematics, computational and theoretical statistics, and risk theory.
The third presentation, titled “Integrating Machine Learning and Benford’s Law: A Conceptual Perspective on Anomaly Detection”, was presented by Dr Dragana Radojičić. She is an Assistant Professor at the University of Belgrade – Faculty of Economics and Business (Department of Statistics and Mathematics). She obtained a PhD in Mathematics at the Vienna University of Technology. Her research mainly focuses on applied, computational, and theoretical probability and statistics, and machine learning.
The presentations were followed by a Q&A and a discussion, moderated by the Chair Prof. Dr. Vesna Rajić.
Chair: Prof. Dr. Vesna Rajić
The webinar was hosted via Zoom and required registation to attend. The full recording can be found below. In order to learn about future webinars, you can sign up to our newsletter by clicking "Subscribe" at the top of the page.
Statistics and Nonlinear Analysis: Simulation and Computation
Guest Editor: Prof. Dr. Vesna Rajić
Deadline for manuscript submissions: 30 September 2025