Omar Fawzi

Omar Fawzi

Auto-generated profile, based on publicly available information

Omar Fawzi

Inria, ENS de Lyon, UCBL, LIP, Lyon Cedex 07, France

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2017
Verified
Conference Paper
Closed access
SMSeyed-Mohsen Moosavi-Dezfooli
Seyed-Mohsen Moosavi-Dezfooli
AFAlhussein Fawzi
Alhussein Fawzi
OFOmar Fawzi
Omar Fawzi
PFPascal Frossard
Pascal Frossard
Given a state-of-the-art deep neural network classifier, we show the existence of a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability. We propose a systematic algorithm for computing universal perturbations, and show that state-of-the-art deep neural networks are highly vulnerable to such perturbations, albeit being quasi-imperceptible to the human eye. We further empirically analyze these universal perturbations and show, in particular, that they generalize very well across neural networks. The surprising existence of universal perturbations reveals important geometric correlations among the high-dimensional decision boundary of classifiers. It further outlines potential security breaches with the existence of single directions in the input space that adversaries can possibly exploit to break a classifier on most natural images.

9 September 2015 in Communications in Mathematical Physics
Verified
Journal Article
Open access
PDF file
OFOmar Fawzi
Omar Fawzi
RRRenato Renner
Renato Renner
A state on a tripartite quantum system \({A \otimes B \otimes C}\) forms a Markov chain if it can be reconstructed from its marginal on \({A \otimes B}\) by a quantum operation from B to \({B \otimes C}\). We show that the quantum conditional mutual information I(A : C|B) of an arbitrary state is an upper bound on its distance to the closest reconstructed state. It thus quantifies how well the Markov chain property is approximated.

31 January 2018 in Nature Communications
Verified
Journal Article
Open access
PDF file
RARotem Arnon-Friedman
Rotem Arnon-Friedman
FDFrédéric Dupuis
Frédéric Dupuis
OFOmar Fawzi
Omar Fawzi
RRRenato Renner
Renato Renner
TVThomas Vidick
Thomas Vidick
Device-independent cryptography goes beyond conventional quantum cryptography by providing security that holds independently of the quality of the underlying physical devices. Device-independent protocols are based on the quantum phenomena of non-locality and the violation of Bell inequalities. This high level of security could so far only be established under conditions which are not achievable experimentally. Here we present a property of entropy, termed “entropy accumulation”, which asserts that the total amount of entropy of a large system is the sum of its parts. We use this property to prove the security of cryptographic protocols, including device-independent quantum key distribution, while achieving essentially optimal parameters. Recent experimental progress, which enabled loophole-free Bell tests, suggests that the achieved parameters are technologically accessible. Our work hence provides the theoretical groundwork for experimental demonstrations of device-independent cryptography.

25 August 2017 in Machine Learning
Verified
Journal Article
Closed access
PDF file
AFAlhussein Fawzi
Alhussein Fawzi
OFOmar Fawzi
Omar Fawzi
PFPascal Frossard
Pascal Frossard

23 September 2020 in Communications in Mathematical Physics
Verified
Journal Article
Open access
PDF file
FDFrédéric Dupuis
Frédéric Dupuis
OFOmar Fawzi
Omar Fawzi
RRRenato Renner
Renato Renner
We ask the question whether entropy accumulates, in the sense that the operationally relevant total uncertainty about an n-partite system $$A = (A_1, \ldots A_n)$$ A = ( A 1 , … A n ) corresponds to the sum of the entropies of its parts $$A_i$$ A i . The Asymptotic Equipartition Property implies that this is indeed the case to first order in n—under the assumption that the parts $$A_i$$ A i are identical and independent of each other. Here we show that entropy accumulation occurs more generally, i.e., without an independence assumption, provided one quantifies the uncertainty about the individual systems $$A_i$$ A i by the von Neumann entropy of suitably chosen conditional states. The analysis of a large system can hence be reduced to the study of its parts. This is relevant for applications. In device-independent cryptography, for instance, the approach yields essentially optimal security bounds valid for general attacks, as shown by Arnon-Friedman et al. (SIAM J Comput 48(1):181–225, 2019).

18 September 2015 in Communications in Mathematical Physics
Verified
Journal Article
Closed access
PDF file
WBWinton Brown
Winton Brown
OFOmar Fawzi
Omar Fawzi