96 citations · 152 across the 20 of their papers we have counts for
25 papers
Reward-Preserving Attacks For Robust Reinforcement Learning
Lucas Schott, Elies Gherbi, Hatem Hajri +1
Adversarial training in reinforcement learning (RL) is challenging because perturbations cascade through trajectories and compound over time, making fixed-strength attacks either o…
Towards stable AI systems for Evaluating Arabic Pronunciations
Hadi Zaatiti, Hatem Hajri, Osama Abdullah +1
Modern Arabic ASR systems such as wav2vec 2.0 excel at word- and sentence-level transcription, yet struggle to classify isolated letters. In this study, we show that this phoneme-l…
Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey
Lucas Schott, Josephine Delas, Hatem Hajri +5
Deep Reinforcement Learning (DRL) is a subfield of machine learning for training autonomous agents that take sequential actions across complex environments. Despite its significant…
SEEDS: Exponential SDE Solvers for Fast High-Quality Sampling from Diffusion Models
Martin Gonzalez, Nelson Fernandez, Thuy Tran +3
A potent class of generative models known as Diffusion Probabilistic Models (DPMs) has become prominent. A forward diffusion process adds gradually noise to data, while a model lea…
Noisy Learning for Neural ODEs Acts as a Robustness Locus Widening
Martin Gonzalez, Hatem Hajri, Loic Cantat +1
We investigate the problems and challenges of evaluating the robustness of Differential Equation-based (DE) networks against synthetic distribution shifts. We propose a novel and s…
Riemannian data-dependent randomized smoothing for neural networks certification
Pol Labarbarie, Hatem Hajri, Marc Arnaudon
Certification of neural networks is an important and challenging problem that has been attracting the attention of the machine learning community since few years. In this paper, we…
Realization Theory Of Recurrent Neural ODEs Using Polynomial System Embeddings
Martin Gonzalez, Thibault Defourneau, Hatem Hajri +1
In this paper we show that neural ODE analogs of recurrent (ODE-RNN) and Long Short-Term Memory (ODE-LSTM) networks can be algorithmically embeddeded into the class of polynomial s…
Improving Robustness of Deep Reinforcement Learning Agents: Environment Attack based on the Critic Network
Lucas Schott, Hatem Hajri, Sylvain Lamprier
To improve policy robustness of deep reinforcement learning agents, a line of recent works focus on producing disturbances of the environment. Existing approaches of the literature…
Stochastic sparse adversarial attacks
Manon Césaire, Lucas Schott, Hatem Hajri +2
This paper introduces stochastic sparse adversarial attacks (SSAA), standing as simple, fast and purely noise-based targeted and untargeted attacks of neural network classifiers (N…
Probabilistic Jacobian-based Saliency Maps Attacks
Théo Combey, António Loison, Maxime Faucher +1
Neural network classifiers (NNCs) are known to be vulnerable to malicious adversarial perturbations of inputs including those modifying a small fraction of the input features named…
Geomstats: A Python Package for Riemannian Geometry in Machine Learning
Nina Miolane, Alice Le Brigant, Johan Mathe +16
We introduce Geomstats, an open-source Python toolbox for computations and statistics on nonlinear manifolds, such as hyperbolic spaces, spaces of symmetric positive definite matri…
FRSign: A Large-Scale Traffic Light Dataset for Autonomous Trains
Jeanine Harb, Nicolas Rébéna, Raphaël Chosidow +3
In the realm of autonomous transportation, there have been many initiatives for open-sourcing self-driving cars datasets, but much less for alternative methods of transportation su…
From Node Embedding To Community Embedding : A Hyperbolic Approach
Thomas Gerald, Hadi Zaatiti, Hatem Hajri +2
Detecting communities on graphs has received significant interest in recent literature. Current state-of-the-art community embedding approach called \textit{ComE} tackles this prob…
Automatic generation of ground truth for the evaluation of obstacle detection and tracking techniques
Hatem Hajri, Emmanuel Doucet, Marc Revilloud +3
As automated vehicles are getting closer to becoming a reality, it will become mandatory to be able to characterise the performance of their obstacle detection systems. This valida…
Real Time Lidar and Radar High-Level Fusion for Obstacle Detection and Tracking with evaluation on a ground truth
Hatem Hajri, Mohamed-Cherif Rahal
- Both Lidars and Radars are sensors for obstacle detection. While Lidars are very accurate on obstacles positions and less accurate on their velocities, Radars are more precise on…
Gaussian distributions on Riemannian symmetric spaces: statistical learning with structured covariance matrices
Salem Said, Hatem Hajri, Lionel Bombrun +1
The Riemannian geometry of covariance matrices has been essential to several successful applications, in computer vision, biomedical signal and image processing, and radar data pro…
Application of Stochastic Flows to the Sticky Brownian Motion Equation
Hatem Hajri, Caglar Mine, Marc Arnaudon
We show how the theory of stochastic flows allows to recover in an elementary way a well known result of Warren on the sticky Brownian motion equation.
On a coupling of solutions to the interface SDE on a star graph
Hatem Hajri, Marc Arnaudon
Inspired by Tsirelson proof of the non Brownian character of WalshBrownian motion ltration on three or more rays, we prove some results on aparticular coupling of solutions to the…
On flows associated to Tanaka's SDE and related works
Hatem Hajri
We review the construction of flows associated to Tanaka's SDE from [9] and give an easy proof of the classification of these flows by means of probability measures on [0, 1]. Our…
Stochastic flows and an interface SDE on metric graphs
Hatem Hajri, Olivier Raimond
This paper consists in the study of a stochastic differential equation on a metric graph, called an interface SDE . To each edge of the graph is associated an indepe…
Stochastic flows on metric graphs
Hatem Hajri, Olivier Raimond
We study a simple stochastic differential equation driven by one Brownian motion on a general oriented metric graph whose solutions are stochastic flows of kernels. Under some cond…
On the Csáki-Vincze transformation
Hatem Hajri
Cs aki and Vincze have de fined in 1961 a discrete transformation T which applies to simple random walks and is measure preserving. In this paper, we are interested in ergodic and…
Tanaka's equation on the circle and stochastic flows
Hatem Hajri, Olivier Raimond
We define a Tanaka's equation on an oriented graph with two edges and two vertices. This graph will be embedded in the unit circle. Extending this equation to flows of kernels, we…
Discrete approximation to solution flows of Tanaka SDE related to Walsh Brownian motion
Hatem Hajri
In a previous work, we have defined a Tanaka SDE related to Walsh Brownian motion which depends on kernels. It was shown that there are only one Wiener solution and only one flow o…