Picture for Seyed-Mohsen Moosavi-Dezfooli

Seyed-Mohsen Moosavi-Dezfooli

Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attribution

Add code
Nov 12, 2024
Viaarxiv icon

Geometric Inductive Biases of Deep Networks: The Role of Data and Architecture

Add code
Oct 15, 2024
Viaarxiv icon

Certified Human Trajectory Prediction

Add code
Mar 20, 2024
Viaarxiv icon

How to choose your best allies for a transferable attack?

Add code
Apr 05, 2023
Figure 1 for How to choose your best allies for a transferable attack?
Figure 2 for How to choose your best allies for a transferable attack?
Figure 3 for How to choose your best allies for a transferable attack?
Figure 4 for How to choose your best allies for a transferable attack?
Viaarxiv icon

Revisiting DeepFool: generalization and improvement

Add code
Mar 22, 2023
Figure 1 for Revisiting DeepFool: generalization and improvement
Figure 2 for Revisiting DeepFool: generalization and improvement
Figure 3 for Revisiting DeepFool: generalization and improvement
Figure 4 for Revisiting DeepFool: generalization and improvement
Viaarxiv icon

The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training

Add code
Nov 01, 2022
Figure 1 for The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training
Figure 2 for The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training
Figure 3 for The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training
Figure 4 for The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training
Viaarxiv icon

PRIME: A Few Primitives Can Boost Robustness to Common Corruptions

Add code
Dec 27, 2021
Figure 1 for PRIME: A Few Primitives Can Boost Robustness to Common Corruptions
Figure 2 for PRIME: A Few Primitives Can Boost Robustness to Common Corruptions
Figure 3 for PRIME: A Few Primitives Can Boost Robustness to Common Corruptions
Figure 4 for PRIME: A Few Primitives Can Boost Robustness to Common Corruptions
Viaarxiv icon

Vehicle trajectory prediction works, but not everywhere

Add code
Dec 07, 2021
Figure 1 for Vehicle trajectory prediction works, but not everywhere
Figure 2 for Vehicle trajectory prediction works, but not everywhere
Figure 3 for Vehicle trajectory prediction works, but not everywhere
Figure 4 for Vehicle trajectory prediction works, but not everywhere
Viaarxiv icon

Are socially-aware trajectory prediction models really socially-aware?

Add code
Aug 24, 2021
Figure 1 for Are socially-aware trajectory prediction models really socially-aware?
Figure 2 for Are socially-aware trajectory prediction models really socially-aware?
Figure 3 for Are socially-aware trajectory prediction models really socially-aware?
Figure 4 for Are socially-aware trajectory prediction models really socially-aware?
Viaarxiv icon

Adversarial training may be a double-edged sword

Add code
Jul 24, 2021
Figure 1 for Adversarial training may be a double-edged sword
Figure 2 for Adversarial training may be a double-edged sword
Figure 3 for Adversarial training may be a double-edged sword
Viaarxiv icon