Linear Digressions

How to Steal a Model

Linear Digressions

What does it mean to steal a model? It means someone (the thief, presumably) can re-create the predictions of the model without having access to the algorithm itself, or the training data. Sound far-fetched? It isn't. If that person can ask for predictions from the model, and he (or she) asks just the right questions, the model can be reverse-engineered right out from under you. Relevant links: https://www.usenix.org/system/files/conference/usenixsecurity16/sec16_paper_tramer.pdf

Next Episodes

Linear Digressions

Regularization @ Linear Digressions

📆 2016-10-03 04:13 / 00:17:27


Linear Digressions

The Cold Start Problem @ Linear Digressions

📆 2016-09-26 04:24 / 00:15:37


Linear Digressions

Open Source Software for Data Science @ Linear Digressions

📆 2016-09-19 06:27 / 00:20:05


Linear Digressions

Scikit + Optimization = Scikit-Optimize @ Linear Digressions

📆 2016-09-12 03:54 / 00:15:41


Linear Digressions

Two Cultures: Machine Learning and Statistics @ Linear Digressions

📆 2016-09-05 03:50 / 00:17:29