Warnings of Cyber Threats And Active Risk Management

Tuesday, February 14, 2023
12:00 PM - 1:00 PM
(Pacific)
Speaker: 
  • Dr. Marie-Elisabeth Paté-Cornell
headshot of marie-elisabeth pate-cornell on cardinal background

Join the Cyber Policy Center, together with the Program on Democracy and the Internet on Tuesday, February 14, from Noon–1 PM Pacific, for a discussion with Dr. Marie-Elisabeth Paté-Cornell. The session will moderated by Andrew Grotto who directs the Program on Geopolitics, Technology, and Governance.

Paté-Cornell will present a warning systems model in which early-stage cyber threat signals are generated using machine learning and artificial intelligence (AI) techniques. The risk management team is hybrid: a "robot" and a human technician who can take over when the uncertainties or the consequences of failure are too large. Active cyber security is most often, in practice, reactive. Based on the manual forensics of machine-generated data by humans, security efforts only begin after a loss has taken place but the current security paradigm can be significantly improved. Cyber-threat behaviors can be modeled as a set of discrete, observable steps called a ‘kill chain.’ Data produced from observing early kill-chain steps can support the automation of manual defensive responses before an attack causes losses. Using the concept of  a system gate set, a model of access control decisions, cyber security experts can effectively conduct risk assessments of their systems, which can inform effective policies. This approach unifies core concepts from decision analysis and machine learning by combining machine learning and decision risk attitudes. An early warning system using these techniques has the potential to avoid more sever downstream consequences as it can disrupt threats of an attack at the beginning of the kill chain.

This session is part of the Winter Seminar Series, a series spanning January through March, hosted at the Cyber Policy Center with the Program on Democracy and the Internet. Sessions are in-person and virtual, with in-person attendance offered to Stanford affiliates only. Lunch is provided for in-person attendance.

In person attendance is available to Stanford affiliates and virtual attendance via zoom is open to the public; registration is required.

About the Speaker

Dr. Marie-Elisabeth Paté-Cornell is the Burt and Deedee McMurtry Professor in the School of Engineering and a Senior Fellow (by courtesy) of the Stanford Freeman-Spogli Institute for International Studies. Her specialty is engineering risk analysis, with applications to complex systems (space, medical, offshore oil platforms, cyber security, etc.). Her work has been based on probabilistic and stochastic models and on Artificial Intelligence. She is a member of the National Academy of Engineering, the French Académie des Technologies, the NASA Advisory Council, and a Distinguished Visiting Scientist of the Jet Propulsion Lab. She was a member of the President’s Foreign Intelligence Advisory Board (2001 to 2008). She holds a BS in Mathematics and Physics, Marseille (France), an Engineering degree (Applied Math/CS) from the Institut Polytechnique de Grenoble (France), an MS in Operations Research (OR) and a PhD in Engineering-Economic Systems (EES), both from Stanford University. She is the author or coauthor of numerous publications including several Best Paper awards. She was awarded the 2002 Distinguished Achievement Award of the Society for Risk Analysis (of which she is a Fellow), the INFORMS Ramsey Medal of Decision Analysis  (2010), an Honorary PhD from the University of Strathclyde (2016), and the IEEE Ramo medal for Systems Engineering and Science in 2021. Her recent work focuses on cyber security for specific systems and spacecraft design and monitoring.