Alexandre Araujo

aaraujo001gmail.com

Last update June 2024

I recently finished my postdoc in the EnSuRe Research Group at NYU. I worked with Siddharth Garg and Farshad Khorrami on Trustworthy Machine Learning. I am currently looking for a Research Scientist/Engineer position. Prior to that, I was a postdoctoral researcher at INRIA and École Normale Supérieure (ENS) in the WILLOW project-team in Paris, France. I obtained my PhD in Computer Science in June 2021 at Université Paris Dauphine-PSL where I was advised by Pr. Jamal Atif, Pr. Yann Chevaleyre and Dr. Benjamin Negrevergne.
Google Scholar
Github
Resume
Research
Fine-grained Local Sensitivity Analysis of Standard Dot-Product Self-Attention
A. Havens, A. Araujo, H. Zhang and B. Hu
ICML • 2024
paper • bibtex
PAL: Proxy-Guided Black-Box Attack on Large Language Models
C. Sitawarin, N. Mu, D. Wagner and A. Araujo
preprint • 2024
paper • code • bibtex
LipSim: A Provably Robust Perceptual Similarity Metric
S. Ghazanfari, A. Araujo, P. Krishnamurthy, F. Khorrami and S. Garg
ICLR • 2024
paper • code • bibtex
On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural Networks
Z. Wang, A. Havens, A. Araujo, Y. Zheng, B. Hu, Y. Chen and S. Jha
ICLR • 2024
paper • code • bibtex
The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing
B. Delattre, A. Araujo, Q. Barthélemy and A. Allauzen
ICLR • 2024
paper • bibtex
Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations
P. Pauli, A. Havens, A. Araujo, S. Garg, F. Khorrami, F. Allgower and B. Hu
ICLR • 2024
paper • code • bibtex
Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
H. Xue, A. Araujo, B. Hu and Y. Chen
NeurIPS • 2023
paper • code • bibtex
Exploiting Connections between Lipschitz Structures for Certifiably Robust Deep Equilibrium Models
A. Havens, A. Araujo, S. Garg, F. Khorrami and B. Hu
NeurIPS • 2023
paper • code • bibtex
R-LPIPS: An Adversarially Robust Perceptual Similarity Metric
S. Ghazanfari, S. Garg, P. Krishnamurthy, F. Khorrami and A. Araujo
ICML Workshop on New Frontiers in Adversarial Machine Learning • 2023
paper • code • bibtex
Certification of Deep Learning Models for Medical Image Segmentation
O. Laousy, A. Araujo, G. Chassagnon, N. Paragios, M. Revel and M. Vakalopoulou
MICCAI • 2023
paper • bibtex
Towards Better Certified Segmentation via Diffusion Models
O. Laousy, A. Araujo, G. Chassagnon, M. Revel, S. Garg, F. Khorrami and M. Vakalopoulou
UAI • 2023
paper • code • bibtex
Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration
B. Delattre, Q. Barthelemy, A. Araujo and A. Allauzen
ICML • 2023
paper • code • bibtex
A Unified Algebraic Perspective on Lipschitz Neural Networks
A. Araujo*, A. Havens*, B. Delattre, A. Allauzen and B. Hu
ICLR • 2023 — Spotlight
paper • bibtex
Towards Evading the Limits of Randomized Smoothing: A Theoretical Analysis
R. Ettedgui*, A. Araujo*, R. Pinot, Y. Chevaleyre and J. Atif
Preprint • 2022
paper • bibtex
A Dynamical System Perspective for Lipschitz Neural Networks
L. Meunier*, B. Delattre*, A. Araujo* and A. Allauzen
ICML • 2022 — ORAL
paper • bibtex
Building Compact and Robust Deep Neural Networks with Toeplitz Matrices
A. Araujo
PhD Thesis • 2021
paper • bibtex
On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory
A. Araujo, B. Negrevergne, Y. Chevaleyre and J. Atif
AAAI • 2020
paper • code • bibtex
Advocating for Multiple Defense Strategies against Adversarial Examples
A. Araujo, L. Menuier, R. Pinot and B. Negrevergne
ECML - Workshops • 2020
paper • bibtex
Theoretical Evidence for Adversarial Robustness through Randomization
R. Pinot, L. Meunier, A. Araujo, H. Kashima, F. Yger, C. Gouy-Pailler and J. Atif
NeurIPS • 2019
paper • code • bibtex
Understanding and Training Deep Diagonal Circulant Neural Networks
A. Araujo, B. Negrevergne, Y. Chevaleyre and J. Atif
ECAI • 2019
paper • bibtex
Training Compact Deep Learning Models for Video Classification using Circulant Matrices
A. Araujo, B. Negrevergne, Y. Chevaleyre and J. Atif
ECCV - Workshops • 2018
paper • code • bibtex