The Conference for Machine Learning Innovation

Privacy Preserving Machine Learning

Join the ML Revolution! Register until September 26th: ✓Arduino Starter Kit or C64 Mini for free ✓Save up to € 300 ✓ 10% Team Discount Register Now

Privacy Preserving Machine Learning is a subfield of Machine Learning in which the training of the model happens in a way such that the privacy of the data is preserved. Various approaches already exist but are not well established. At the same time, privacy considerations become more important. Among the approaches is Federated Learning for a decentralized training, whereby the data can stay at the place of origin and only learning updates respectively gradient updates are exchanged. Another approach is Deferentially Private Stochastic Gradient Descent whereby the learning algorithm of the neural network is modified so that single training examples do not affect the model too much. Thus, limited inference can be made from the model to the data it was trained on. In this talk we will understand both approaches and have a look on how to implement them with the help of TensorFlow.

Behind the Tracks