Authors
Florian Tramèr, Fan Zhang, Ari Juels, Michael K Reiter, Thomas Ristenpart
Publication date
2016
Conference
25th USENIX security symposium (USENIX Security 16)
Pages
601-618
Description
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.
Scholar articles
F Tramèr, F Zhang, A Juels, MK Reiter, T Ristenpart - 25th USENIX security symposium (USENIX Security 16 …, 2016