skip to main content
research-article
Free Access

Learning securely

Published:28 October 2016Publication History
Skip Abstract Section

Abstract

Because it is easy to fool, machine learning must be taught how to handle adversarial inputs.

References

  1. Goodfellow, I., Shlens, J., and Szegedy, C. Explaining and Harnessing Adversarial Examples http://arxiv.org/pdf/1412.6572v3.pdf.Google ScholarGoogle Scholar
  2. Kantchelian, A., Tygar, J. D., and Joseph, A. Evasion and Hardening of Tree Ensemble Classifiers http://arxiv.org/pdf/1509.07892.pdf Google ScholarGoogle ScholarDigital LibraryDigital Library
  3. Miyato, T., Dai, A., and Goodfellow, I. Virtual Adversarial Training for Semi-Supervised Text Classification http://arxiv.org/pdf/1605.07725v1.pdf.Google ScholarGoogle Scholar
  4. Papernot, N., McDaniel, P., Wu, X., Jha, X., and Swami, A. Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks Proceedings of the 37th IEEE Symposium on Security and Privacy, May 2016.Google ScholarGoogle Scholar
  5. Papernot, N., McDaniel, P., and Goodfellow, I. Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples http://arxiv.org/pdf/1605.07277v1.pdf.Google ScholarGoogle Scholar
  6. Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., and Fergus, R. Intriguing Properties of Neural Networks https://arxiv.org/pdf/1312.6199v4.pdf.Google ScholarGoogle Scholar

Index Terms

  1. Learning securely

      Recommendations

      Comments

      Login options

      Check if you have access through your login credentials or your institution to get full access on this article.

      Sign in

      Full Access

      • Published in

        cover image Communications of the ACM
        Communications of the ACM  Volume 59, Issue 11
        November 2016
        118 pages
        ISSN:0001-0782
        EISSN:1557-7317
        DOI:10.1145/3013530
        • Editor:
        • Moshe Y. Vardi
        Issue’s Table of Contents

        Copyright © 2016 ACM

        Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

        Publisher

        Association for Computing Machinery

        New York, NY, United States

        Publication History

        • Published: 28 October 2016

        Permissions

        Request permissions about this article.

        Request Permissions

        Check for updates

        Qualifiers

        • research-article
        • Popular
        • Pre-selected

      PDF Format

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      HTML Format

      View this article in HTML Format .

      View HTML Format