conference paper · IEEE Symposium on Security and Privacy (S&P) · 2018

Stealing Hyperparameters in Machine Learning

Cited by 510Open access

Abstract

Hyperparameters are critical in machine learning, as different hyperparameters often result in models with significantly different performance. Hyperparameters may be deemed confidential because of their commercial value and the confidentiality of the proprietary algorithms that the learner uses to learn them. In this work, we propose attacks on stealing the hyperparameters that are learned by a learner. We call our attacks hyperparameter stealing attacks. Our attacks are applicable to a variety of popular machine learning algorithms such as ridge regression, logistic regression, support vector machine, and neural network. We evaluate the effectiveness of our attacks both theoretically and empirically. For instance, we evaluate our attacks on Amazon Machine Learning. Our results demonstrate that our attacks can accurately steal hyperparameters. We also study countermeasures. Our results highlight the need for new defenses against our hyperparameter stealing attacks for certain machine learning algorithms.

Cite this paper

APA 7

Wang, B., & Gong, N. Z. (2018). Stealing Hyperparameters in Machine Learning. IEEE Symposium on Security and Privacy (S&P), 36–52. https://doi.org/10.1109/sp.2018.00038

MLA 9

Wang, Binghui, and Neil Zhenqiang Gong. “Stealing Hyperparameters in Machine Learning.” IEEE Symposium on Security and Privacy (S&P), 2018, pp. 36–52, https://doi.org/10.1109/sp.2018.00038.

Chicago

Wang, Binghui, and Neil Zhenqiang Gong. 2018. “Stealing Hyperparameters in Machine Learning.” IEEE Symposium on Security and Privacy (S&P): 36–52. https://doi.org/10.1109/sp.2018.00038.

Harvard

Wang, B. and Gong, N.Z. (2018) ‘Stealing Hyperparameters in Machine Learning’, IEEE Symposium on Security and Privacy (S&P), pp. 36–52. Available at: https://doi.org/10.1109/sp.2018.00038.

BibTeX

@article{wang2018stealing,
  title = {{Stealing Hyperparameters in Machine Learning}},
  author = {Wang, Binghui and Gong, Neil Zhenqiang},
  journal = {IEEE Symposium on Security and Privacy (S&P)},
  pages = {36--52},
  year = {2018},
  doi = {10.1109/sp.2018.00038}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.