Adversarial training is the coolest thing since sliced bread. –Yan LeCun (Quora Session) Little preface: A little background first. Traditional neural networks have an interconnected layer of computing nodes where in the first layer various input signals of the training data are fed and in the final layer are select number of nodes(each representing a class/category) each representing the probability of given data being into that certain category. Between the first and the last layer are n numbers of additional layers where input signals flow from one layer to another based on some cost function and other computations that follow along the connections (represented by weight of the connection).