Publications

Conference Publications

A geometry-inspired decision-based attack

Y. Liu; S. M. Moosavi Dezfooli; P. Frossard 

2019. ICCV 2019 : IEEE International Conference on Computer Vision, Seoul, South Korea, Oct 27, 2019 – Nov 3, 2019.

Universal Adversarial Attacks on Text Classifiers

M. Behjati; S. M. Moosavi Dezfooli; M. Soleymani Baghshah; P. Frossard 

2019. 44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, 2019.

Robustness via curvature regularization, and vice versa

S. M. Moosavi Dezfooli; A. Fawzi; J. Uesato; P. Frossard 

2019. IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, California, USA, 2019.

SparseFool: a few pixels make a big difference

A. Modas; S. M. Moosavi Dezfooli; P. Frossard 

2019. IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, California, USA, 2019.

Adaptive Quantization for Deep Neural Network

Y. Zhou; S. M. Moosavi Dezfooli; N-M. Cheung; P. Frossard 

2018-03-19. 32nd AAAI Conference on Artificial Intelligence / 30th Innovative Applications of Artificial Intelligence Conference / 8th AAAI Symposium on Educational Advances in Artificial Intelligence, New Orleans, LA, February 02-07, 2018. p. 4596-4604.

Geometric robustness of deep networks: analysis and improvement

C. Kanbak; S. M. Moosavi Dezfooli; P. Frossard 

2018. IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, USA, 2018. DOI : 10.1109/CVPR.2018.00467.

Empirical study of the topology and geometry of deep networks

A. Fawzi; S. M. Moosavi Dezfooli; P. Frossard; S. Soatto 

2018. IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, USA, 2018. DOI : 10.1109/CVPR.2018.00396.

Robustness of Classifiers to Universal Perturbations: A Geometric Perspective

S. M. Moosavi Dezfooli; A. Fawzi; F. Omar; P. Frossard; S. Soatto 

2018. Sixth International Conference on Learning Representations (ICLR), Vancouver, Canada, 2018.

Universal adversarial perturbations

S. M. Moosavi Dezfooli; A. Fawzi; O. Fawzi; P. Frossard 

2017. IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawaii, USA, 2017. DOI : 10.1109/Cvpr.2017.17.

Robustness of classifiers: from adversarial to random noise

A. Fawzi; S. M. Moosavi Dezfooli; P. Frossard 

2016. 30th Annual Conference on Neural Information Processing Systems (NIPS), Barcelona, Spain, December 5-10, 2016.

DeepFool: a simple and accurate method to fool deep neural networks

S. M. Moosavi Dezfooli; A. Fawzi; P. Frossard 

2016. IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, USA, 2016.

Journal Papers

The Robustness of Deep Networks – A geometric perspective

A. Fawzi; S. M. Moosavi Dezfooli; P. Frossard 

IEEE Signal Processing Magazine. 2017. Vol. 34, num. 6, p. 50-62. DOI : 10.1109/Msp.2017.2740965.

Pre-prints

A geometry-inspired decision-based attack

Y. Liu; S. M. Moosavi Dezfooli; P. Frossard 

2019

Robustness via curvature regularization, and vice versa

S. M. Moosavi Dezfooli; A. Fawzi; J. Uesato; P. Frossard 

2018

SparseFool: a few pixels make a big difference

A. Modas; S. M. Moosavi Dezfooli; P. Frossard 

2018