← Authors

Seyed-Mohsen Moosavi-Dezfooli

20 papers · 2016–2025 · 6 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (6) πŸƒ Academic Marathon (9) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (31) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🧬 Topic Evolution 🀝 Dynamic Duo (12) πŸ”¬ Deep Specialist (10) πŸš€ Conference Pioneer πŸ’Ž Century Club (20) πŸ—ƒοΈ Keyword Collector (59) πŸ”₯ Unstoppable (10) πŸ“ˆ Trend Setter ❓ The Questioner (2)

Conferences

CVPR (10) ICLR (3) NIPS (3) ICCV (2) ECCV (1) ICML (1)

Top co-authors

Pascal Frossard (12) Alhussein Fawzi (6) Omar Fawzi (2) Alexandre Alahi (2) Stefano Soatto (2) Saeed Saadatnejad (2) Rahul Rade (2) Mohammadhossein Bahari (2) Guillermo Ortiz-Jimenez (2) Apostolos Modas (2)

Keywords

adversarial example (6) decision boundary (6) adversarial attack (4) adversarial training (4) adversarial robustness (4) adversarial perturbation (3) image classification (3) neural tangent kernel (2) black-box attack (2) neural network robustness (2) trajectory prediction (2) deep neural network (2) generative model (2) autonomous vehicle (2) neural network (2) loss landscape (1) query efficiency (1) computer vision (1) domain adaptation (1) autonomous driving (1)

Papers

Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture ICLR 2025
Certified Human Trajectory Prediction CVPR 2025
SuperDeepFool: a new fast and accurate minimal adversarial attack NIPS 2024
The Enemy of My Enemy Is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training CVPR 2023
How to Choose your Best Allies for a Transferable Attack? ICCV 2023
Vehicle Trajectory Prediction Works, but Not Everywhere CVPR 2022
PRIME: A Few Primitives Can Boost Robustness to Common Corruptions ECCV 2022
Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off ICLR 2022
Uniform Convergence, Adversarial Spheres and a Simple Remedy ICML 2021
What can linearized neural networks actually say about generalization? NIPS 2021
GeoDA: A Geometric Framework for Black-Box Adversarial Attacks CVPR 2020
A Geometry-Inspired Decision-Based Attack ICCV 2019
Robustness via Curvature Regularization, and Vice Versa CVPR 2019
SparseFool: A Few Pixels Make a Big Difference CVPR 2019
Empirical Study of the Topology and Geometry of Deep Networks CVPR 2018
Geometric Robustness of Deep Networks: Analysis and Improvement CVPR 2018
Robustness of Classifiers to Universal Perturbations: A Geometric Perspective ICLR 2018
Universal Adversarial Perturbations CVPR 2017
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks CVPR 2016
Robustness of classifiers: from adversarial to random noise NIPS 2016