Alexandre Araujo
14 papers · 2019–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
🗺️ Taxonomy Completionist (25) 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🏆 Grand Slam
🧬
Topic Evolution
🏆
Keyword Champion
(6)
🧭
Keyword Pioneer
🏆
Grand Slam
🗃️
Keyword Collector
(54)
🔥
Unstoppable · Bronze
⚡
Prolific Year · Productive
💎
Century Club · Bronze
Top co-authors
Research topics
Machine Learning
(12)
Deep Learning
(9)
Optimization & Theory · Machine Learning
(9)
Artificial Intelligence
(7)
Core AI
(7)
Architectures
(4)
Application Areas
(3)
Learning Types
(3)
Optimization & Theory · Deep Learning
(3)
Computer Vision
(2)
Models
(2)
Techniques
(2)
Mathematics & Optimization
(1)
Analysis
(1)
Core Methods
(1)
Keywords
adversarial robustness
(6)
lipschitz constant
(6)
certified robustness
(4)
adversarial attack
(3)
semidefinite programming
(3)
diffusion model
(2)
vision transformer
(2)
neural network
(2)
randomized smoothing
(2)
convolutional neural network
(2)
model safety
(1)
image retrieval
(1)
dynamical system
(1)
projected gradient descent
(1)
spectral norm
(1)
deep equilibrium model
(1)
memory efficiency
(1)
spectral method
(1)
monte carlo sampling
(1)
neural network optimization
(1)
Papers
Stronger Universal and Transferable Attacks by Suppressing Refusals
NAACL 2025
Fine-grained Local Sensitivity Analysis of Standard Dot-Product Self-Attention
ICML 2024
LipSim: A Provably Robust Perceptual Similarity Metric
ICLR 2024
Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations
ICLR 2024
On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural Networks
ICLR 2024
The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing
ICLR 2024
A Unified Algebraic Perspective on Lipschitz Neural Networks
ICLR 2023
Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
NeurIPS 2023
Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration
ICML 2023
Exploiting Connections between Lipschitz Structures for Certifiably Robust Deep Equilibrium Models
NeurIPS 2023
Towards better certified segmentation via diffusion models
UAI 2023
A Dynamical System Perspective for Lipschitz Neural Networks
ICML 2022
On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory
AAAI 2021
Theoretical evidence for adversarial robustness through randomization
NeurIPS 2019