Dmitrii Usynin

MEng Computing

E-Mail: sends e-mail)


I am a PhD student in a Joint Academy of Doctoral Studies (JADS) at Imperial College London and TU Munich. My main research focus is on adversarial influence in the context of collaborative machine learning. I am currently working on topics such as: attacks on collaborative learning systems, adversarial robustness of ML models, federated learning, differential privacy and collaborative learning for medical imaging. I am a privacy researcher at OpenMined, working on federated learning and differential privacy in healthcare. My recent works “End-to-end privacy preserving deep learning on multi-institutional medical imaging” and “Adversarial interference and its mitigations in privacy-preserving collaborative machine learning” were published in Nature Machine Intelligence. I graduated from Imperial College London with an MEng in Computing and a distinguished project with the title of “Privacy-Preserving Machine Learning in a Medical Domain”.


2016-2020 MEng Computing - Imperial College London


  • attacks on machine learning models
  • differntial privacy
  • collaborative machine learning
  • trustworthy artificial intelligence


Die vollständige Publikationsliste finden Sie unter Google Scholar.