Alexandre Araujo

According to our database, Alexandre Araujo authored at least 26 papers between 2018 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

PAL: Proxy-Guided Black-Box Attack on Large Language Models.

Chawin Sitawarin, Norman Mu, David A. Wagner, Alexandre Araujo

CoRR, 2024

Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations.

Patricia Pauli, Aaron J. Havens, Alexandre Araujo, Siddharth Garg, Farshad Khorrami, Frank Allgöwer, Bin Hu

CoRR, 2024

2023

Towards Real-World Focus Stacking with Deep Learning.

Alexandre Araujo, Jean Ponce, Julien Mairal

CoRR, 2023

LipSim: A Provably Robust Perceptual Similarity Metric.

Sara Ghazanfari, Alexandre Araujo, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg

CoRR, 2023

The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing.

Blaise Delattre, Alexandre Araujo, Quentin Barthélemy, Alexandre Allauzen

CoRR, 2023

R-LPIPS: An Adversarially Robust Perceptual Similarity Metric.

Sara Ghazanfari, Siddharth Garg, Prashanth Krishnamurthy, Farshad Khorrami, Alexandre Araujo

CoRR, 2023

Towards better certified segmentation via diffusion models.

Othmane Laousy, Alexandre Araujo, Guillaume Chassagnon, Marie-Pierre Revel, Siddharth Garg, Farshad Khorrami, Maria Vakalopoulou

Proceedings of the Uncertainty in Artificial Intelligence, 2023

Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability.

Haotian Xue, Alexandre Araujo, Bin Hu, Yongxin Chen

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Exploiting Connections between Lipschitz Structures for Certifiably Robust Deep Equilibrium Models.

Aaron J. Havens, Alexandre Araujo, Siddharth Garg, Farshad Khorrami, Bin Hu

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Certification of Deep Learning Models for Medical Image Segmentation.

Othmane Laousy, Alexandre Araujo, Guillaume Chassagnon, Nikos Paragios, Marie-Pierre Revel, Maria Vakalopoulou

Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2023, 2023

Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration.

Blaise Delattre, Quentin Barthélemy, Alexandre Araujo, Alexandre Allauzen

Proceedings of the International Conference on Machine Learning, 2023

A Unified Algebraic Perspective on Lipschitz Neural Networks.

Alexandre Araujo, Aaron J. Havens, Blaise Delattre, Alexandre Allauzen, Bin Hu

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Towards Evading the Limits of Randomized Smoothing: A Theoretical Analysis.

Raphael Ettedgui, Alexandre Araujo, Rafael Pinot, Yann Chevaleyre, Jamal Atif

CoRR, 2022

A Dynamical System Perspective for Lipschitz Neural Networks.

Laurent Meunier, Blaise Delattre, Alexandre Araujo, Alexandre Allauzen

Proceedings of the International Conference on Machine Learning, 2022

2021

Building Compact and Robust Deep Neural Networks with Toeplitz Matrices. (Construire des réseaux neuronaux profonds compacts et robustes avec des matrices Toeplitz).

Alexandre Araujo

PhD thesis, 2021

Scalable Lipschitz Residual Networks with Convex Potential Flows.

Laurent Meunier, Blaise Delattre, Alexandre Araujo, Alexandre Allauzen

CoRR, 2021

Building Compact and Robust Deep Neural Networks with Toeplitz Matrices.

Alexandre Araujo

CoRR, 2021

On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory.

Alexandre Araujo, Benjamin Négrevergne, Yann Chevaleyre, Jamal Atif

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

Fast & Accurate Method for Bounding the Singular Values of Convolutional Layers with Application to Lipschitz Regularization.

Alexandre Araujo, Benjamin Négrevergne, Yann Chevaleyre, Jamal Atif

CoRR, 2020

Advocating for Multiple Defense Strategies Against Adversarial Examples.

Alexandre Araujo, Laurent Meunier, Rafael Pinot, Benjamin Négrevergne

Proceedings of the ECML PKDD 2020 Workshops, 2020

Understanding and Training Deep Diagonal Circulant Neural Networks.

Alexandre Araujo, Benjamin Négrevergne, Yann Chevaleyre, Jamal Atif

Proceedings of the ECAI 2020 - 24th European Conference on Artificial Intelligence, 29 August-8 September 2020, Santiago de Compostela, Spain, August 29 - September 8, 2020, 2020

2019

Robust Neural Networks using Randomized Adversarial Training.

Alexandre Araujo, Rafael Pinot, Benjamin Négrevergne, Laurent Meunier, Yann Chevaleyre, Florian Yger, Jamal Atif

CoRR, 2019

Theoretical evidence for adversarial robustness through randomization: the case of the Exponential family.

Rafael Pinot, Laurent Meunier, Alexandre Araujo, Hisashi Kashima, Florian Yger, Cédric Gouy-Pailler, Jamal Atif

CoRR, 2019

On the Expressive Power of Deep Fully Circulant Neural Networks.

Alexandre Araujo, Benjamin Négrevergne, Yann Chevaleyre, Jamal Atif

CoRR, 2019

Theoretical evidence for adversarial robustness through randomization.

Rafael Pinot, Laurent Meunier, Alexandre Araujo, Hisashi Kashima, Florian Yger, Cédric Gouy-Pailler, Jamal Atif

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

2018

Training Compact Deep Learning Models for Video Classification Using Circulant Matrices.

Alexandre Araujo, Benjamin Négrevergne, Yann Chevaleyre, Jamal Atif

Proceedings of the Computer Vision - ECCV 2018 Workshops, 2018