Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Out-distribution Training Confers Robustness to Deep Neural Networks
mahdieh abbasi, christian gagne
Feb 12, 2018 (modified: Jun 04, 2018)ICLR 2018 Workshop Submissionreaders: everyoneShow Bibtex
Abstract:The easiness at which adversarial instances can be generated in deep neural networks raises some fundamental questions on their functioning and concerns on their use in critical systems. In this paper, we draw a connection between over-generalization and adversaries: a possible cause of adversaries lies in models designed to make decisions all over the input space, leading to inappropriate high-confidence decisions in parts of the input space not represented in the training set. We empirically show an augmented neural network, which is not trained on any types of adversaries, can increase the robustness by detecting black-box one-step adversaries, i.e. assimilated to out-distribution samples, and making generation of white-box one-step adversaries harder.
Enter your feedback below and we'll get back to you as soon as possible.