Theo dõi
Alexandre Araujo
Alexandre Araujo
New York University
Email được xác minh tại nyu.edu - Trang chủ
Tiêu đề
Trích dẫn bởi
Trích dẫn bởi
Năm
Theoretical evidence for adversarial robustness through randomization
R Pinot, L Meunier, A Araujo, H Kashima, F Yger, C Gouy-Pailler, J Atif
Neural Information Processing Systems (NeurIPS), 2019
1092019
A Unified Algebraic Perspective on Lipschitz Neural Networks
A Araujo, AJ Havens, B Delattre, A Allauzen, B Hu
International Conference on Learning Representations (ICLR), 2023
552023
A Dynamical System Perspective for Lipschitz Neural Networks
L Meunier, B Delattre, A Araujo, A Allauzen
International Conference on Machine Learning (ICML), 2022
542022
Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
H Xue, A Araujo, B Hu, Y Chen
Neural Information Processing Systems (NeurIPS), 2023
532023
Pal: Proxy-guided black-box attack on large language models
C Sitawarin, N Mu, D Wagner, A Araujo
arXiv preprint arXiv:2402.09674, 2024
422024
Robust neural networks using randomized adversarial training
A Araujo, L Meunier, R Pinot, B Negrevergne
arXiv preprint arXiv:1903.10219, 2019
372019
On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory
A Araujo, B Negrevergne, Y Chevaleyre, J Atif
Proceedings of the AAAI Conference on Artificial Intelligence, 2020
342020
R-LPIPS: An Adversarially Robust Perceptual Similarity Metric
S Ghazanfari, S Garg, P Krishnamurthy, F Khorrami, A Araujo
2nd ICML Workshop on New Frontiers in Adversarial Machine Learning, 2023
232023
Training compact deep learning models for video classification using circulant matrices
A Araujo, B Negrevergne, Y Chevaleyre, J Atif
The European Conference on Computer Vision (ECCV) Workshops, 2018
192018
Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration
B Delattre, Q Barthélemy, A Araujo, A Allauzen
International Conference on Machine Learning (ICML), 2023
142023
Advocating for multiple defense strategies against adversarial examples
A Araujo, L Meunier, R Pinot, B Negrevergne
ECML PKDD 2020 Workshops, 2020
122020
On the scalability and memory efficiency of semidefinite programs for Lipschitz constant estimation of neural networks
Z Wang, AJ Havens, A Araujo, Y Zheng, B Hu, Y Chen, S Jha
International Conference on Learning Representations (ICLR), 2024
102024
Exploiting Connections between Lipschitz Structures for Certifiably Robust Deep Equilibrium Models
AJ Havens, A Araujo, S Garg, F Khorrami, B Hu
Neural Information Processing Systems (NeurIPS), 2023
92023
LipSim: A Provably Robust Perceptual Similarity Metric
S Ghazanfari, A Araujo, P Krishnamurthy, F Khorrami, S Garg
International Conference on Learning Representations (ICLR), 2024
82024
Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations
P Pauli, A Havens, A Araujo, S Garg, F Khorrami, F Allgöwer, B Hu
International Conference on Learning Representations (ICLR), 2024
52024
Towards Better Certified Segmentation via Diffusion Models
O Laousy, A Araujo, G Chassagnon, MP Revel, S Garg, F Khorrami, ...
Conference on Uncertainty in Artificial Intelligence (UAI), 2023
52023
The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing
B Delattre, A Araujo, Q Barthélemy, A Allauzen
International Conference on Learning Representations (ICLR), 2024
42024
Towards evading the limits of randomized smoothing: A theoretical analysis
R Ettedgui, A Araujo, R Pinot, Y Chevaleyre, J Atif
arXiv preprint arXiv:2206.01715, 2022
42022
Understanding and Training Deep Diagonal Circulant Neural Networks
A Araujo, B Negrevergne, Y Chevaleyre, J Atif
European Conference on Artificial Intelligence (ECAI), 2019
4*2019
Towards Real-World Focus Stacking with Deep Learning
A Araujo, J Ponce, J Mairal
arXiv preprint arXiv:2311.17846, 2023
22023
Hệ thống không thể thực hiện thao tác ngay bây giờ. Hãy thử lại sau.
Bài viết 1–20