Adversarial machine learning

Posted on September 11, 2016September 11, 2016Author John MountCategories Opinion, StatisticsTags adversarial machine learningI just got back from a very good conference organized by startup.ml: Adversarial Machine Learning. Please read on for my to comments on part of one of the very good talks. Classic machine learning (especially as it is taught in classes) emphasizes a nice safe static environment where you are given some unchanging data and are asked to produce a nice predictive model one time. It is formally easier that casual inference or statistical inference as being right often is enough, no matter what the reason. It lives in an overly idealized world where one implicitly assumes the following simplifying assumptions: The world does not know you are trying to model it (and so can’t take counter-measures,…


Link to Full Article: Adversarial machine learning