Alexandre Araujo

41 papers A* 12A 2Journal 22Unranked 4

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	EMMA: Efficient Visual Alignment in Multi-Modal LLMs. Trans. Mach. Learn. Res. Sara Ghazanfari, Alexandre Araujo, Prashanth Krishnamurthy, Siddharth Garg, Farshad Khorrami
2025	—	`conf`	Stronger Universal and Transferable Attacks by Suppressing Refusals. NAACL (Long Papers) David Huang, Avidan Shah, Alexandre Araujo, David A. Wagner, Chawin Sitawarin
2024	J	`jnl`	EMMA: Efficient Visual Alignment in Multi-Modal LLMs. CoRR Sara Ghazanfari, Alexandre Araujo, Prashanth Krishnamurthy, Siddharth Garg, Farshad Khorrami
2024	A*	`conf`	Fine-grained Local Sensitivity Analysis of Standard Dot-Product Self-Attention. ICML Aaron J. Havens, Alexandre Araujo, Huan Zhang, Bin Hu
2024	A*	`conf`	LipSim: A Provably Robust Perceptual Similarity Metric. ICLR Sara Ghazanfari, Alexandre Araujo, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg
2024	A*	`conf`	Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations. ICLR Patricia Pauli, Aaron J. Havens, Alexandre Araujo, Siddharth Garg, Farshad Khorrami, Frank Allgöwer, Bin Hu
2024	J	`jnl`	Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations. CoRR Patricia Pauli, Aaron J. Havens, Alexandre Araujo, Siddharth Garg, Farshad Khorrami, Frank Allgöwer, Bin Hu
2024	A*	`conf`	On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural Networks. ICLR Zi Wang, Bin Hu, Aaron J. Havens, Alexandre Araujo, Yang Zheng, Yudong Chen, Somesh Jha
2024	J	`jnl`	PAL: Proxy-Guided Black-Box Attack on Large Language Models. CoRR Chawin Sitawarin, Norman Mu, David A. Wagner, Alexandre Araujo
2024	A*	`conf`	The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing. ICLR Blaise Delattre, Alexandre Araujo, Quentin Barthélemy, Alexandre Allauzen
2023	A*	`conf`	A Unified Algebraic Perspective on Lipschitz Neural Networks. ICLR Alexandre Araujo, Aaron J. Havens, Blaise Delattre, Alexandre Allauzen, Bin Hu
2023	J	`jnl`	A Unified Algebraic Perspective on Lipschitz Neural Networks. CoRR Alexandre Araujo, Aaron J. Havens, Blaise Delattre, Alexandre Allauzen, Bin Hu
2023	—	`conf`	Certification of Deep Learning Models for Medical Image Segmentation. MICCAI (4) Othmane Laousy, Alexandre Araujo, Guillaume Chassagnon, Nikos Paragios, Marie-Pierre Revel, Maria Vakalopoulou
2023	J	`jnl`	Certification of Deep Learning Models for Medical Image Segmentation. CoRR Othmane Laousy, Alexandre Araujo, Guillaume Chassagnon, Nikos Paragios, Marie-Pierre Revel, Maria Vakalopoulou
2023	A*	`conf`	Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability. NeurIPS Haotian Xue, Alexandre Araujo, Bin Hu, Yongxin Chen
2023	J	`jnl`	Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability. CoRR Haotian Xue, Alexandre Araujo, Bin Hu, Yongxin Chen
2023	A*	`conf`	Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration. ICML Blaise Delattre, Quentin Barthélemy, Alexandre Araujo, Alexandre Allauzen
2023	J	`jnl`	Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration. CoRR Blaise Delattre, Quentin Barthélemy, Alexandre Araujo, Alexandre Allauzen
2023	A*	`conf`	Exploiting Connections between Lipschitz Structures for Certifiably Robust Deep Equilibrium Models. NeurIPS Aaron J. Havens, Alexandre Araujo, Siddharth Garg, Farshad Khorrami, Bin Hu
2023	J	`jnl`	LipSim: A Provably Robust Perceptual Similarity Metric. CoRR Sara Ghazanfari, Alexandre Araujo, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg
2023	J	`jnl`	R-LPIPS: An Adversarially Robust Perceptual Similarity Metric. CoRR Sara Ghazanfari, Siddharth Garg, Prashanth Krishnamurthy, Farshad Khorrami, Alexandre Araujo
2023	J	`jnl`	The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing. CoRR Blaise Delattre, Alexandre Araujo, Quentin Barthélemy, Alexandre Allauzen
2023	J	`jnl`	Towards Better Certified Segmentation via Diffusion Models. CoRR Othmane Laousy, Alexandre Araujo, Guillaume Chassagnon, Marie-Pierre Revel, Siddharth Garg, Farshad Khorrami, Maria Vakalopoulou
2023	J	`jnl`	Towards Real-World Focus Stacking with Deep Learning. CoRR Alexandre Araujo, Jean Ponce, Julien Mairal
2023	A	`conf`	Towards better certified segmentation via diffusion models. UAI Othmane Laousy, Alexandre Araujo, Guillaume Chassagnon, Marie-Pierre Revel, Siddharth Garg, Farshad Khorrami, Maria Vakalopoulou
2022	A*	`conf`	A Dynamical System Perspective for Lipschitz Neural Networks. ICML Laurent Meunier, Blaise Delattre, Alexandre Araujo, Alexandre Allauzen
2022	J	`jnl`	Towards Evading the Limits of Randomized Smoothing: A Theoretical Analysis. CoRR Raphael Ettedgui, Alexandre Araujo, Rafael Pinot, Yann Chevaleyre, Jamal Atif
2021	J	`jnl`	Building Compact and Robust Deep Neural Networks with Toeplitz Matrices. CoRR Alexandre Araujo
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
2021	A*	`conf`	On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory. AAAI Alexandre Araujo, Benjamin Négrevergne, Yann Chevaleyre, Jamal Atif
2021	J	`jnl`	Scalable Lipschitz Residual Networks with Convex Potential Flows. CoRR Laurent Meunier, Blaise Delattre, Alexandre Araujo, Alexandre Allauzen
2020	—	`conf`	Advocating for Multiple Defense Strategies Against Adversarial Examples. PKDD/ECML Workshops Alexandre Araujo, Laurent Meunier, Rafael Pinot, Benjamin Négrevergne
2020	J	`jnl`	Advocating for Multiple Defense Strategies against Adversarial Examples. CoRR Alexandre Araujo, Laurent Meunier, Rafael Pinot, Benjamin Négrevergne
2020	J	`jnl`	Fast & Accurate Method for Bounding the Singular Values of Convolutional Layers with Application to Lipschitz Regularization. CoRR Alexandre Araujo, Benjamin Négrevergne, Yann Chevaleyre, Jamal Atif
2020	A	`conf`	Understanding and Training Deep Diagonal Circulant Neural Networks. ECAI Alexandre Araujo, Benjamin Négrevergne, Yann Chevaleyre, Jamal Atif
2019	J	`jnl`	On the Expressive Power of Deep Fully Circulant Neural Networks. CoRR Alexandre Araujo, Benjamin Négrevergne, Yann Chevaleyre, Jamal Atif
2019	J	`jnl`	Robust Neural Networks using Randomized Adversarial Training. CoRR Alexandre Araujo, Rafael Pinot, Benjamin Négrevergne, Laurent Meunier, Yann Chevaleyre, Florian Yger, Jamal Atif
2019	A*	`conf`	Theoretical evidence for adversarial robustness through randomization. NeurIPS Rafael Pinot, Laurent Meunier, Alexandre Araujo, Hisashi Kashima, Florian Yger, Cédric Gouy-Pailler, Jamal Atif
2019	J	`jnl`	Theoretical evidence for adversarial robustness through randomization: the case of the Exponential family. CoRR Rafael Pinot, Laurent Meunier, Alexandre Araujo, Hisashi Kashima, Florian Yger, Cédric Gouy-Pailler, Jamal Atif
2018	—	`conf`	Training Compact Deep Learning Models for Video Classification Using Circulant Matrices. ECCV Workshops (4) Alexandre Araujo, Benjamin Négrevergne, Yann Chevaleyre, Jamal Atif
2018	J	`jnl`	Training compact deep learning models for video classification using circulant matrices. CoRR Alexandre Araujo, Benjamin Négrevergne, Yann Chevaleyre, Jamal Atif