Privacy-preserving machine learning in TensorFlow with TF Encrypted
Morten Dahl reviews modern cryptographic techniques such as homomorphic encryption and multiparty computation, sharing concrete examples in TensorFlow using the open source library TF Encrypted. Join in to learn how to get started with privacy-preserving techniques today, without needing to master the cryptography.
| Talk Title | Privacy-preserving machine learning in TensorFlow with TF Encrypted |
| Speakers | Morten Dahl (Dropout Labs) |
| Conference | O’Reilly Artificial Intelligence Conference |
| Conf Tag | Put AI to Work |
| Location | New York, New York |
| Date | April 16-18, 2019 |
| URL | Talk Page |
| Slides | Talk Slides |
| Video | |
Machine learning applied to healthcare or otherwise sensitive data may be blocked if privacy isn’t adequately addressed. Morten Dahl reviews modern cryptographic techniques such as homomorphic encryption and multiparty computation, sharing concrete examples in TensorFlow using the open source library TF Encrypted. You’ll discover how to make predictions without exposing the prediction input and how to fit a model without ever exposing the training data. Join in to learn how to get started with privacy-preserving techniques today, without needing to master the cryptography.
