The Limitations of Deep Learning in Adversarial Settings

  title={The Limitations of Deep Learning in Adversarial Settings},
  author={Nicolas Papernot and Patrick D. McDaniel and Somesh Jha and Matt Fredrikson and Z. Berkay Celik and Ananthram Swami},
  journal={2016 IEEE European Symposium on Security and Privacy (EuroS&P)},
Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfections in the training phase of deep neural networks make them vulnerable to adversarial samples: inputs crafted by adversaries with the intent of causing deep neural networks to misclassify. In this work, we formalize the space of adversaries against deep neural networks (DNNs) and introduce a novel class of… CONTINUE READING
Highly Influential
This paper has highly influenced 82 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 593 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 139 times over the past 90 days. VIEW TWEETS


Publications citing this paper.
Showing 1-10 of 413 extracted citations

593 Citations

Citations per Year
Semantic Scholar estimates that this publication has 593 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.

Similar Papers

Loading similar papers…