Machine Learning in Adversarial Settings

IEEE Security and Privacy

Volumn 14, Issue 3, 2016, Pages 68-72

  McDaniel, Patrick ^a   Papernot, Nicolas ^a   Celik, Z Berkay ^a  

^a PENNSYLVANIA STATE UNIVERSITY   (United States)

Author keywords

adversarial machine learning; machine learning; machine learning security; security; system security

Indexed keywords

ARTIFICIAL INTELLIGENCE;

COMPUTATIONAL STRUCTURE; MACHINE LEARNING COMMUNITIES; NOVEL TECHNIQUES; SECURITY; SYSTEM SECURITY; UNDERLYING CAUSE;

LEARNING SYSTEMS;

EID: 84973354134     PISSN: 15407993     EISSN: 15584046     Source Type: Journal    
DOI: 10.1109/MSP.2016.51     Document Type: Article

References (8)

1. C. Szegedy et al, "Intriguing Properties of Neural Networks, " Proc. Int'l Conf. Learning Representations (ICLR 14), 2014; htp://arxiv.org/abs/1312.6199.
2. I.J. Goodfellow, J. Shlens, and C. Szegedy, "Explaining and Harnessing Adversarial Examples, " Proc. Int'l Conf. Learning Representations (ICLR 15), 2015; htp://arxiv.org/abs/1412.6572.
3. N. Papernot et al., "Te Limitations of Deep Learning in Adversarial Setings, " Proc. 1st IEEE European Symp. Security and Privacy (EuroS&P 16), 2016; htp://arxiv.org/abs/1511.07528.
4. P. Laskov and R. Lippmann, "Machine Learning in Adversarial Environments, " Machine Learning, vol. 81, no. 2, 2010, pp. 115-119.
5. M. Kearns and M. Li, "Learning in the Presence of Malicious Errors, " J. Computing, vol. 22, no. 4, 1993, pp. 807-837.
6. D. Lowd and C. Meek, "Adversarial Learning, " Proc. Knowledge Discovery in Data Mining (SIGKDD 05), 2005, pp. 641-647.
7. B.A. Nelson, "Behavior of Machine Learning Algorithms in Adversarial Environments, " PhD thesis, Dept. of Computer Science, Univ. California, Berkeley, 2010.
8. N. Papernot et al., "Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks, " to be published in Proc. 37th IEEE Symp. Security and Privacy, 2016.