vincentliuheyang / Steal-ML

Model extraction attacks on Machine-Learning-as-a-Service platforms.

Python implementation of extraction attacks against Machine Learning models, as described in the following paper:

Stealing Machine Learning Models via Prediction APIs
Florian Tramèr, Fan Zhang, Ari Juels, Michael Reiter and Thomas Ristenpart
USENIX Security Symposium, 2016.

The conference paper and presentation slides will appear shortly here:
https://www.usenix.org/conference/usenixsecurity16/technical-sessions/presentation/tramer

REQUIREMENTS

Some of the experiments require an active AWS or BigML account.
Other requirements can be found in the correponding project folder.

CONTACT

Questions and suggestions can be sent to [e-mail]