190 citations · 950 across the 19 of their papers we have counts for
9 papers · 1 filter
Learning dynamic polynomial proofs
Alhussein Fawzi, Mateusz Malinowski, Hamza Fawzi +1
Polynomial inequalities lie at the heart of many mathematical disciplines. In this paper, we consider the fundamental computational task of automatically searching for proofs of po…
Are Labels Required for Improving Adversarial Robustness?
Jonathan Uesato, Jean-Baptiste Alayrac, Po-Sen Huang +3
Recent work has uncovered the interesting (and somewhat surprising) finding that training models to be invariant to adversarial perturbations requires substantially larger datasets…
Verification of deep probabilistic models
Krishnamurthy Dvijotham, Marta Garnelo, Alhussein Fawzi +1
Probabilistic models are a critical part of the modern deep learning toolbox - ranging from generative models (VAEs, GANs), sequence to sequence models used in machine translation…
Robustness via curvature regularization, and vice versa
Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Jonathan Uesato +1
State-of-the-art classifiers have been shown to be largely vulnerable to adversarial perturbations. One of the most effective strategies to improve robustness is adversarial traini…
Robustness of classifiers to uniform and Gaussian noise
Jean-Yves Franceschi, Alhussein Fawzi, Omar Fawzi
We study the robustness of classifiers to various kinds of random noise models. In particular, we consider noise drawn uniformly from the ball for and…
Adversarial vulnerability for any classifier
Alhussein Fawzi, Hamza Fawzi, Omar Fawzi
Despite achieving impressive performance, state-of-the-art classifiers remain highly vulnerable to small, imperceptible, adversarial perturbations. This vulnerability has proven em…
Robustness of classifiers: from adversarial to random noise
Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard
Several recent works have shown that state-of-the-art classifiers are vulnerable to worst-case (i.e., adversarial) perturbations of the datapoints. On the other hand, it has been e…
DeepFool: a simple and accurate method to fool deep neural networks
Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Pascal Frossard
State-of-the-art deep neural networks have achieved impressive results on many image classification tasks. However, these same architectures have been shown to be unstable to small…
Analysis of classifiers' robustness to adversarial perturbations
Alhussein Fawzi, Omar Fawzi, Pascal Frossard
The goal of this paper is to analyze an intriguing phenomenon recently discovered in deep networks, namely their instability to adversarial perturbations (Szegedy et. al., 2014). W…