Stealing Machine Learning Models via Prediction APIs. Florian Tramèr, École Polytechnique Fédérale de Lausanne (EPFL); Fan Zhang, Cornell University; Ari Juels, Cornell Tech; Michael K. Reiter, The University of North Carolina at Chapel Hill; Thomas Ristenpart, Cornell Tech. This paper is included in the Proceedings of the 25th USENIX Security Symposium August 10–12, 2016. Austin, TX ISB N 978 -1-931971-32-4.

“Machine learning (ML) models may be deemed confidential due to their sensitive training data, commercial value, or use in security applications. Increasingly often, confidential ML models are being deployed with publicly accessible query interfaces. ML-as-a-service (“predictive analytics”) systems are an example: Some allow users to train models on potentially sensitive data and charge others for access on a pay-per-query basis. The tension between model confidentiality and pub-lic access motivates our investigation of model extraction attacks. In such attacks, an adversary with black-box access, but no prior knowledge of an ML model’s parameters or training data, aims to duplicate the functionalityof (i.e., “steal”) the model. Unlike in classical learning theory settings, ML-as-a-service offerings may accept partial feature vectors as inputs and include confidence values with predictions. Given these practices, we show simple, efficient attacks that extract target ML models with near-perfect fidelity for popular model classes including logistic regression, neural networks, and decision trees. We demonstrate these attacks against the online services of BigML and Amazon Machine Learning. We further show that the natural countermeasure of omitting confidence values from model outputs still admits potentially harmful model extraction attacks. Our results highlight the need for careful ML model deployment and new model extraction countermeasures.”