University of Louisville (Dr. Roman Yampolskiy's Research Group (Cybersecurity Lab))
A university research lab at the University of Louisville directed by Dr. Roman Yampolskiy, one of the founders of the field of AI safety, conducting research on the theoretical limits of AI controllability, AI containment, and cybersecurity.
A university research lab at the University of Louisville directed by Dr. Roman Yampolskiy, one of the founders of the field of AI safety, conducting research on the theoretical limits of AI controllability, AI containment, and cybersecurity.
People
Updated 05/18/26Founder and Director
Funding Details
Updated 05/18/26- Annual Budget
- -
- Current Runway
- -
- Funding Goal
- -
- Funding Raised to Date
- -
Org Details
Updated 05/18/26The Cyber Security Lab at the University of Louisville is a research lab in the Department of Computer Engineering and Computer Science at the J.B. Speed School of Engineering, founded and directed by Dr. Roman V. Yampolskiy. Yampolskiy joined the University of Louisville as an assistant professor in 2008 after completing his PhD in Computer Science and Engineering at the University at Buffalo (SUNY), where he was a recipient of a four-year NSF IGERT fellowship. He was promoted to associate professor in 2014 and has served as director of the lab since 2012. Yampolskiy is widely credited with coining the term 'AI safety' in a 2011 publication titled 'Artificial Intelligence Safety Engineering: Why Machine Ethics Is a Wrong Approach,' making him one of the earliest formal researchers in the field. His early work on AI Safety Engineering, AI Containment, and AI Accidents has become foundational and is extensively cited. His current research focuses on the theoretical limits to explainability, predictability, and controllability of advanced intelligent systems, as well as analysis, handling, and prediction of AI accidents and failures. Yampolskiy has authored over 200 publications, including multiple influential books: 'Artificial Superintelligence: a Futuristic Approach' (2015), 'Artificial Intelligence Safety and Security' (2018), 'Taxonomies of Intelligence' (2023), 'AI: Unexplainable, Unpredictable, Uncontrollable' (2024), and 'Considerations on the AI Endgame' (2025, co-authored with Soenke Ziesche). His work has been cited by over 10,000 scientists and featured in more than 1,000 media reports across 30 languages. He was ranked in the World's Top 2% of Scientists by Stanford University and Scopus/Elsevier in 2023. Beyond his university role, Yampolskiy serves as a Research Advisor to the Machine Intelligence Research Institute (MIRI), an AI Safety Fellow at the Foresight Institute, and a Research Associate at the Global Catastrophic Risk Institute (GCRI). He is a Senior Member of IEEE and an alumnus of Singularity University. His public engagement includes appearances on the Lex Fridman Podcast (2024) and the Joe Rogan Experience (2025), where he discussed the risks of artificial superintelligence. He received the Lifeboat Foundation Guardian Award in 2025 for his contributions to warning about existential risks from AI. The lab's research has been funded by the National Science Foundation, the National Security Agency, the Department of Homeland Security, EA Ventures, and the Future of Life Institute. The lab also pioneered the field of Artimetrics, aimed at identifying, classifying, and authenticating robots, software, and virtual reality agents for security purposes.
Theory of Change
Updated 05/18/26Yampolskiy's research group operates on the premise that advanced AI systems are fundamentally uncontrollable, and that establishing the theoretical limits of AI controllability, explainability, and predictability is essential for informing policy and guiding the development of AI safety measures. By producing rigorous academic research demonstrating impossibility results and fundamental limitations in AI control, the lab aims to provide the scientific basis for arguments in favor of extreme caution in AI development, including potential moratoriums on building artificial superintelligence. The group also contributes to public awareness through books, media appearances, and speaking engagements, helping policymakers and the public understand the severity of existential risks from advanced AI.
Grants Received
Updated 05/18/26Projects– no linked projects
Updated 05/18/26Discussion
Key risk: The focus on fundamental uncontrollability and advocating moratoria is strategically contentious and may yield limited actionable alignment or policy wins, and given his existing visibility and low funding needs the marginal counterfactual impact of additional funding could be small.
Case for funding: Yampolskiy’s lab is one of the few academic groups publishing rigorous impossibility results on AI controllability and detailed accident analyses, and he can convert that scholarship into outsized policy and public influence through major platforms (Lex Fridman, Joe Rogan) and books, with high leverage per dollar via funding PhD students.