Like in many other scientific domains, academic research in cybersecurity has been profoundly influenced by recent advances in artificial intelligence, particularly by the widespread adoption of machine learning models and their integration into a large number of products. Only a few years ago, AI-centric papers were relatively rare in top academic venues; today, it is difficult to find a paper that does not include at least some application of machine learning.

In this talk, we will explore some of the impacts that this trend has had on the research conducted at the uOttawa–IBM Cyber Range. We will begin by examining examples of vulnerabilities introduced by these models, and how deploying them hastily can make systems less secure. We will focus on two specific cases: first, the surprising weaknesses of face recognition systems, similar to those routinely used worldwide to unlock smartphones; and second, the ability to poison diffusion models—the same models capable of generating ultra-realistic scenes from simple prompts.

We will then turn to the positive side of AI and discuss how it can enhance cybersecurity. In our work, we have explored how models can help produce more secure code. We will present a system we developed to detect specific vulnerabilities in intermediate code, and, given the growing reliance on large language models for code generation, we will conclude by discussing a benchmark we created to evaluate these models’ ability to identify and “understand” insecure code.

Bio: Guy-Vincent Jourdan is a full professor of computer science at the Faculty of Engineering at the University of Ottawa, Canada, and the co-director of the uOttawa–IBM Cyber Range. He joined the School of Electrical Engineering and Computer Science as an associate professor in June 2004, after seven years in the private sector as CTO and later CEO of the Ottawa-based company Decision Academic Graphics. He received his Ph.D. from l’Université de Rennes / INRIA in France in 1995, in the area of distributed systems analysis. He now has over 20 years of experience leading research and industry collaborations in the field of cybersecurity, with a focus on cybercrime detection and prevention. His collaborators include industry leaders such as IBM, Cisco, Fortinet, and OpenText. He has co-authored over 120 scientific publications and holds 19 patents in partnership with various companies. His long-standing collaboration with IBM Security teams around the world has earned numerous accolades, including four “Research Project of the Year” awards (2010, 2012, 2014, 2017), the “Faculty Fellow of the Year” award (2018), and the IBM CAS Canada Award of Excellence (2019). He received the Award for Excellence in Research Partnerships from the Faculty of Engineering at the University of Ottawa in 2023, and he is an IBM Champion in 2025.