Past talk · AI/ML Seminar Series
A Gentle Introduction to Neural Network Verification
Professor of Verification and Formal Guarantees of Machine Learning, Department of Computer Science, TU Dortmund
- Date & time
- Thursday, August 28, 2025 · 1:00 PM
- Location
- Donald Bren Hall 4011
Abstract
Artificial Intelligence has become ubiquitous in modern life. This Cambrian explosion of intelligent systems has been made possible by extraordinary advances in machine learning, especially in training deep neural networks and their ingenious architectures. However, like traditional hardware and software, neural networks often have defects, which are notoriously difficult to detect and correct. Consequently, deploying them in safety-critical settings remains a substantial challenge. Motivated by the success of formal methods in establishing the reliability of safety-critical hardware and software, numerous formal verification techniques for deep neural networks have emerged recently. As a guide through the vibrant and rapidly evolving field of neural network verification, this talk will give an overview of the fundamentals and core concepts of the field, discuss prototypical examples of various existing verification approaches, and showcase how generative AI can improve verification results.
About the speaker
Daniel Neider is Professor of Verification and Formal Guarantees of Machine Learning at the Technical University of Dortmund and an affiliated researcher at the Trustworthy Data Science and Security research center within the University Alliance Ruhr. His research focuses on developing formal methods to ensure the reliability of artificial intelligence and machine learning models. After earning his doctorate from RWTH Aachen University in 2014, he held postdoctoral positions at the University of Illinois at Urbana-Champaign and the University of California, Los Angeles. He later led the Logic and Learning research group at the Max Planck Institute for Software Systems from 2017 to 2022 while teaching at TU Kaiserslautern.