AI applications in security are clear and potentially useful, however they are not without flaws, and present a new and unique attack surface.Namely, if one could truly understand how a certain model works, and the type of features it uses to reach a decision, then there is a potential to deceive it consistently, creating a bypass while maintaining a false sense of security.In this talk, we will walk through our research in which we have reversed engineered Cylance's AI based EPP to create a unique and amusing by