As neural network classifiers become increasingly successful at various tasks ranging from speech recognition and image classification to various natural language processing tasks and even recognizing malware, a second, somewhat disturbing discovery has also been made. It is possible to fool these systems with carefully crafted inputs that appear to the lay observer to be natural data, but cause the neural network to misclassify in random or even targeted ways.

In this talk we will discuss why such attacks are possible, and the problem of designing, identifying, and avoiding attacks by such crafted "adversarial" inputs.