For years, defenders have focused on automation for detecting vulnerabilities and attacks. What if reinforcement learning could help create autonomous defensive agents that are capable of more?
On June 23, CSET Junior Fellow Krystal Jackson and Senior Fellow Andrew Lohn discussed recent trends in research on the use of reinforcement learning for cyber defense, existing tools and how to use them, and the technical limits of today’s capabilities and areas for improvement. Apple’s Melody Wolk moderated the Q&A.
Krystal Jackson is a Visiting Junior Fellow, through Open Philanthropy’s Tech Policy Fellowship, at Georgetown’s Center for Security and Emerging Technology (CSET), where she works on the CyberAI Project. Prior to joining CSET, she was a Public Interest Technology Fellow at Carnegie Mellon University and a Youth Organizing Fellow with Americans United. Her research interests include the impact and future direction of weaponized AI, governance strategies for reducing the risk from advanced technologies, ethics of technology, and methods for value-sensitive design. Krystal holds a M.S. in Information Security Policy & Management and a B.A. in Ethics, History, & Public Policy, both from Carnegie Mellon University.
Andrew Lohn is a Senior Fellow at Georgetown’s Center for Security and Emerging Technology (CSET), where he works on the CyberAI Project. Prior to joining CSET, he was an Information Scientist at the RAND Corporation, where he led research focusing mainly on cybersecurity and artificial intelligence. Prior to RAND, Andrew worked in material science and nanotechnology at Sandia National Laboratories, NASA, Hewlett Packard Labs, and a few startup companies. He has published in a variety of fields and his work has been covered in MIT Technology Review, Gizmodo, Foreign Policy and BBC. He has a PhD in electrical engineering from UC Santa Cruz and a Bachelors in Engineering from McMaster University.
Melody Wolk is a Machine Learning Researcher at Apple. She works on applied and theoretical security research problems, primarily in the realms of cyber defense and security automation. Prior to joining Apple, Melody was an ML engineer at Vectra AI, a cloud-native threat detection and response platform. She published several papers, mostly focusing on the application of Reinforcement Learning in the cybersecurity domain. Before joining the industry, Melody received her PhD in Astrophysics from the Institute of Astrophysics in Paris.