Understanding FGSM Attacks
Explaining how Fast Gradient Sign Method generates adversarial examples.
We break down how gradient-based attacks work, visualize perturbations and measure robustness.
Exploring Projected Gradient Descent (PGD)
Deep dive into one of the most powerful iterative adversarial attack methods.
Understand why PGD is considered the “universal first-order adversary” in adversarial ML research.
