Summary
Seyed-Mohsen (Seyed) Moosavi-Dezfooli is a Lecturer (Assistant Professor) at Imperial College London in the Department of Electrical and Electronic Engineering. His main research interest is reliable/trustworthy machine learning, in particular robustness and interpretability of deep neural networks.
Previously he was a postdoctoral researcher in the Institute for Machine Learning at ETH Zurich (2019-2021). He received his PhD in Computer and Communication Sciences from EPFL (2014-2019). Seyed got his M.Sc. degree in Communication Systems from EPFL in 2014 and his B.Sc. in Electrical Engineering from Tehran Polytechnic in 2012.
A full list of publications can be found on his Google Scholar page.
Selected Publications
Journal Articles
Ortiz-Jimenez G, Modas A, Moosavi-Dezfooli S-M, et al., 2021, Optimism in the Face of Adversity: Understanding and Improving Deep Learning Through Adversarial Robustness, Proceedings of the IEEE, Vol:109, ISSN:0018-9219, Pages:635-659
Conference
Rade R, Moosavi Dezfooli SM, Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off, International Conference on Learning Representations
Moosavi-Dezfooli S-M, Fawzi A, Fawzi O, et al., 2017, Universal Adversarial Perturbations, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE
Moosavi-Dezfooli S-M, Fawzi A, Frossard P, 2016, DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE