Thermometer Encoding One Hot Way To Resist Adversarial Examples ICLR 2018 计算

Published as a conference paper at ICLR 2018THERMOMETER ENCODING: ONE HOT WAY TO RESIST ADVERSARIAL EXAMPLESJacob Buckman∗†, Aurko Roy∗, Colin Raffel, Ian Goodfellow Google Brain Mountain View, CA {buckman, aurkor, craffel, goodfellow}@google.comABSTRACTIt is well known that it is possible to construct “adversarial examples” for neu- ral networks: inputs which are misclassified by the network yet indistinguishable from true data. We propose a simple modification to standard neural network ar- ch