The Labcorp Leadership in Technology Speaker Series welcomes Gary McGraw, co-founder of the Berryville Institute of Machine Learning. McGraw will discuss "Security Engineering for Machine Learning."

Research at the Berryville Institute of Machine Learning is focused on understanding and categorizing security engineering risks introduced by machine learning at the design level. Though the idea of addressing security risk in machine learning is not a new one, most previous work has focused on either particular attacks against running machine learning systems (a kind of dynamic analysis) or operational security issues. This talk will focus on the results of an architectural risk analysis (sometimes called a threat model) of machine learning systems in general. McGraw will present a list of the top five (of 78 known) machine learning systems security risks during the presentation.