Seyed Mohsen Moosavi Dezfooli
EPFL STI IEL LTS4
ELD 241 (Bâtiment ELD)
Station 11
CH-1015 Lausanne
Biography
I received my B.Sc. in Electrical Engineering from Amirkabir University of Technology (Tehran Polytechnic) in 2012. I got my M.Sc. in Communication Systems from EPFL in 2014. Beside my regular master's study, I was working at LCAV as a research assistant on random tomography under the supervision of Prof. Vetterli. I did my master thesis at ABB Corporate Research, Baden-Daettwil. I was working on an accurate and robust indoor positioning scheme which needs as minimum infrastructure as possible. Now, I am working towards my PhD thesis at Signal Processing Laboratory 4 under the supervision of Prof. Frossard.
Education
| Ph.D. | Computer and Communication Sciences | École Polytechnique Fédérale de Lausanne | Sep 2014 - May 2019 |
| M.Sc. | Communication Systems (Signals, Images and Interfaces) | École Polytechnique Fédérale de Lausanne | Sep 2012 - Sep 2014 |
| B.Sc. | Electrical Engineering (Communication Systems) | Amirkabir University of Technology (Tehran Polytechnic) | Sep 2008- Jul 2012 |
Publications
Infoscience
By year
2019
A. Modas; S. M. Moosavi Dezfooli; P. Frossard : SparseFool: a few pixels make a big difference. 2019. IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, California, USA, 2019.
Y. Liu; S. M. Moosavi Dezfooli; P. Frossard : A geometry-inspired decision-based attack. 2019. ICCV 2019 : IEEE International Conference on Computer Vision, Seoul, South Korea, Oct 27, 2019 - Nov 3, 2019.
S. M. Moosavi Dezfooli; A. Fawzi; J. Uesato; P. Frossard : Robustness via curvature regularization, and vice versa. 2019. IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, California, USA, 2019.
M. Behjati; S. M. Moosavi Dezfooli; M. Soleymani Baghshah; P. Frossard : Universal Adversarial Attacks on Text Classifiers. 2019. IEEE ICASSP, Brighton, UK, 2019.
A. Ajalloeian : Stochastic Zeroth-Order Optimisation Algorithms with Variance Reduction. EPFL, 2019-06-21.
2018
C. Kanbak; S. M. Moosavi Dezfooli; P. Frossard : Geometric robustness of deep networks: analysis and improvement. 2018. IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, USA, 2018. DOI : 10.1109/CVPR.2018.00467.
S. M. Moosavi Dezfooli; A. Fawzi; J. Uesato; P. Frossard : Robustness via curvature regularization, and vice versa. 2018.
A. Modas; S. M. Moosavi Dezfooli; P. Frossard : SparseFool: a few pixels make a big difference. 2018.
A. Fawzi; S. M. Moosavi Dezfooli; P. Frossard; S. Soatto : Empirical study of the topology and geometry of deep networks. 2018. IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, USA, 2018. DOI : 10.1109/CVPR.2018.00396.
S. M. Moosavi Dezfooli; A. Fawzi; F. Omar; P. Frossard; S. Soatto : Robustness of Classifiers to Universal Perturbations: A Geometric Perspective. 2018. Sixth International Conference on Learning Representations (ICLR), Vancouver, Canada, 2018.
Y. Zhou; S. M. Moosavi Dezfooli; N.-M. Cheung; P. Frossard : Adaptive Quantization for Deep Neural Network. 2018-03-19. AAAI.
2017
A. Fawzi; S. M. Moosavi Dezfooli; P. Frossard : The Robustness of Deep Networks - A geometric perspective; IEEE Signal Processing Magazine. 2017. DOI : 10.1109/Msp.2017.2740965.
S. M. Moosavi Dezfooli; A. Fawzi; O. Fawzi; P. Frossard : Universal adversarial perturbations. 2017. IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawaii, USA, 2017. DOI : 10.1109/Cvpr.2017.17.
2016
S. M. Moosavi Dezfooli; A. Fawzi; P. Frossard : DeepFool: a simple and accurate method to fool deep neural networks. 2016. IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, USA, 2016.
A. Fawzi; S. M. Moosavi Dezfooli; P. Frossard : Robustness of classifiers: from adversarial to random noise. 2016. 30th Annual Conference on Neural Information Processing Systems (NIPS), Barcelona, Spain, December 5-10, 2016.
S. M. Moosavi Dezfooli; Y.-A. Pignolet-Oswald; D. Dzung : Simultaneous Acoustic Localization of Multiple Smartphones with Euclidean Distance Matrices. 2016. International Conference on Embedded Wireless Systems and Networks, Graz, Austria, February, 2016. p. 41-46.