Dmitrii Usynin

Dmitrii Usynin

PhD Student

Imperial College London

I am a PhD student in a Joint Academy of Doctoral Studies (JADS) at Imperial College London and TU Munich. My research is adversarial influence in the context of collaborative machine learning, specializing in medical imaging. I am open to collaboration on the topics of: Privacy Attacks on AI Systems, Adversarial Robustness of ML Models, Federated Learning, Differential Privacy and Collaborative Learning in Medical Imaging.

I am also a privacy researcher at OpenMined, where I work on Federated Learning and Differential Privacy in Healthcare. My most recent works “Private Deep Learning for Hospitals using Federated Learning and Differential Privacy” and “Privacy-Preserving Medical Image Analysis” were published at PriCon 2020 and MedNeurIPS 2020 respectively.

Interests

  • Artifical Intelligence in Medicine
  • Secure and Private Artificial Intelligence

Education

  • Computing (M.Eng.), 2020

    Imperial College London