For hackers with a focus on real-world applications

With a background in cryptography and privacy, Morten has spent recent years applying and adapting techniques from these fields to machine learning, focusing on practical tools and concrete applications with the aim of making privacy-preserving machine learning more accessible to practitioners. His work has been primarily on federated learning and efficient secure computation for deep learning, including SDA, an open source project for secure aggregation for sporadic devices, and TF Encrypted, an open source project for integrating and experimenting with private-preserving machine learning in TensorFlow.

Morten works as a research scientist at Dropout Labs, a startup focused on building a platform for secure, privacy-preserving machine learning, and is an active maintainer of PPML News and member of the OpenMined community. He holds a MSc in theoretical computer science and a PhD in cryptography, and uses any excuse he can for programming in Rust.

Visit me on Twitter, GitHub, Medium, Keybase, and LinkedIn!