The Limitations of Deep Learning in Adversarial Settings

By Nicolas Papernot, Patrick Drew McDaniel, Somesh Jha, Matt Fredrikson, Z. Berkay Celik, Ananthram Swami. 2015

4,317 citations recorded by the source corpus.

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 algorithms to craft adversarial samples based on a precise understanding of the mapping between inputs and outputs of DNNs. In an application to computer vision, we show that our algorithms can reliably produce samples correctly classified by human subjects but misclassified in specific targets by a DNN with a 97% adversarial success rate while only modifying on average 4.02% of the input features per sample. We then evaluate the vulnerability of different sample classes to adversarial perturbations by defining a hardness measure. Finally, we describe preliminary work outlining defenses against adversarial samples by defining a predictive measure of distance between a benign input and a target classification.

Subfields: Artificial Intelligence, Safety Research, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Percy Liang
  2. Nicholas Carlini
  3. Bernt Schiele
  4. Yoshua Bengio
  5. Mohit Bansal
  6. Quoc V. Le
  7. Sergey Levine
  8. Jianfeng Gao

In Safety Research

  1. Nicolas Papernot
  2. Patrick Drew McDaniel
  3. Nicholas Carlini
  4. Ian J. Goodfellow
  5. Xiaoyu Cao
  6. Reza Shokri
  7. Michael Backes
  8. Jamie Hayes

In Safety, Robustness & Interpretability

  1. Nicholas Carlini
  2. Matthias Hein
  3. Nicolas Papernot
  4. Florian Tramèr
  5. Bo Li
  6. Cho-Jui Hsieh
  7. Bernt Schiele
  8. Aleksander Madry

Citations in the corpus