Seyed-Mohsen Moosavi-Dezfooli

is this you? claim profile

0 followers
EPFL ∙ Apple Inc.

Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness

Driven by massive amounts of data and important advances in computationa...
10/19/2020 ∙ by Guillermo Ortiz-Jiménez, et al. ∙ 5 ∙ share

read it
Neural Anisotropy Directions

In this work, we analyze the role of the network architecture in shaping...
06/17/2020 ∙ by Guillermo Ortiz-Jiménez, et al. ∙ 0 ∙ share

read it
GeoDA: a geometric framework for black-box adversarial attacks

Adversarial examples are known as carefully perturbed images fooling ima...
03/13/2020 ∙ by Ali Rahmati, et al. ∙ 0 ∙ share

read it
Hold me tight! Influence of discriminative features on deep network boundaries

Important insights towards the explainability of neural networks and the...
02/15/2020 ∙ by Guillermo Ortiz-Jiménez, et al. ∙ 4 ∙ share

read it
A geometry-inspired decision-based attack

Deep neural networks have recently achieved tremendous success in image ...
03/26/2019 ∙ by Yujia Liu, et al. ∙ 0 ∙ share

read it
Robustness via curvature regularization, and vice versa

State-of-the-art classifiers have been shown to be largely vulnerable to...
11/23/2018 ∙ by Seyed-Mohsen Moosavi-Dezfooli, et al. ∙ 0 ∙ share

read it
SparseFool: a few pixels make a big difference

Deep Neural Networks have achieved extraordinary results on image classi...
11/06/2018 ∙ by Apostolos Modas, et al. ∙ 0 ∙ share

read it
Divide, Denoise, and Defend against Adversarial Attacks

Deep neural networks, although shown to be a successful class of machine...
02/19/2018 ∙ by Seyed-Mohsen Moosavi-Dezfooli, et al. ∙ 0 ∙ share

read it
Adaptive Quantization for Deep Neural Network

In recent years Deep Neural Networks (DNNs) have been rapidly developed ...
12/04/2017 ∙ by Yiren Zhou, et al. ∙ 0 ∙ share

read it
Geometric robustness of deep networks: analysis and improvement

Deep convolutional neural networks have been shown to be vulnerable to a...
11/24/2017 ∙ by Can Kanbak, et al. ∙ 0 ∙ share

read it
Analysis of universal adversarial perturbations

Deep networks have recently been shown to be vulnerable to universal per...
05/26/2017 ∙ by Seyed-Mohsen Moosavi-Dezfooli, et al. ∙ 0 ∙ share

read it
Classification regions of deep neural networks

The goal of this paper is to analyze the geometric properties of deep ne...
05/26/2017 ∙ by Alhussein Fawzi, et al. ∙ 0 ∙ share

read it
Universal adversarial perturbations

Given a state-of-the-art deep neural network classifier, we show the exi...
10/26/2016 ∙ by Seyed-Mohsen Moosavi-Dezfooli, et al. ∙ 0 ∙ share

read it
Robustness of classifiers: from adversarial to random noise

Several recent works have shown that state-of-the-art classifiers are vu...
08/31/2016 ∙ by Alhussein Fawzi, et al. ∙ 0 ∙ share

read it

Seyed-Mohsen Moosavi-Dezfooli

Featured Co-authors

Stefano Soatto

Pascal Frossard

Ngai-Man Cheung

Huaiyu Dai

Oncel Tuzel

Alhussein Fawzi

Jonathan Uesato

Omar Fawzi

Ashish Shrivastava

Yujia Liu

Guillermo Ortiz-Jiménez

Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness

Neural Anisotropy Directions

GeoDA: a geometric framework for black-box adversarial attacks

Hold me tight! Influence of discriminative features on deep network boundaries

A geometry-inspired decision-based attack

Robustness via curvature regularization, and vice versa

SparseFool: a few pixels make a big difference

Divide, Denoise, and Defend against Adversarial Attacks

Adaptive Quantization for Deep Neural Network

Geometric robustness of deep networks: analysis and improvement

Analysis of universal adversarial perturbations

Classification regions of deep neural networks

Universal adversarial perturbations

Robustness of classifiers: from adversarial to random noise