Keynote: Security Engineering for Machine Learning

Machine Learning has made impressive progress on many tasks including image classification, machine translation, autonomous vehicle control, playing complex games including chess, Go, and Atari video games, and more. This has led to popular press coverage of Artificial Intelligence, and has elevated deep learning to an almost magical status in the eyes of the public. Machine Learning (ML), especially of the deep learning sort, is not magic, however. ML has become so popular that its application, though often poorly understood and partially motivated by hype, is exploding. I am concerned with the systematic risk invoked by adopting ML in a haphazard fashion. Our research at the Berryville Institute of Machine Learning (BIML) is focused on understanding and categorizing security engineering risks introduced by ML at the design level. This talk focuses on two threads: building a taxonomy of known attacks on ML and the results of an architectural risk analysis (sometimes called a threat model) of ML systems in ge