Advanced search
1 file | 1.07 MB

How the Softmax output is misleading for evaluating the strength of adversarial examples

Utku Özbulak (UGent) , Wesley De Neve (UGent) and Arnout Van Messem (UGent)
Author
Organization

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.07 MB

Citation

Please use this url to cite or link to this publication:

Chicago
Özbulak, Utku, Wesley De Neve, and Arnout Van Messem. 2018. “How the Softmax Output Is Misleading for Evaluating the Strength of Adversarial Examples.” In NeurIPS 2018 : 32nd Conference on Neural Information Processing Systems, Papers.
APA
Özbulak, U., De Neve, W., & Van Messem, A. (2018). How the Softmax output is misleading for evaluating the strength of adversarial examples. NeurIPS 2018 : 32nd conference on neural information processing systems, Papers. Presented at the 32nd Conference on Neural Information Processing Systems (NeurIPS 2018) ; Workshop on Security in Machine Learning (SECML 2018).
Vancouver
1.
Özbulak U, De Neve W, Van Messem A. How the Softmax output is misleading for evaluating the strength of adversarial examples. NeurIPS 2018 : 32nd conference on neural information processing systems, Papers. 2018.
MLA
Özbulak, Utku, Wesley De Neve, and Arnout Van Messem. “How the Softmax Output Is Misleading for Evaluating the Strength of Adversarial Examples.” NeurIPS 2018 : 32nd Conference on Neural Information Processing Systems, Papers. 2018. Print.
@inproceedings{8586221,
  author       = {Özbulak, Utku and De Neve, Wesley and Van Messem, Arnout},
  booktitle    = {NeurIPS 2018 : 32nd conference on neural information processing systems, Papers},
  language     = {eng},
  location     = {Montréal, QC, Canada},
  pages        = {9},
  title        = {How the Softmax output is misleading for evaluating the strength of adversarial examples},
  year         = {2018},
}