# ML

Extending FGSM to Other Norms

Fast Gradient Sign Method, with perturbation limited by not only L1, but also...

Link

Adversarial Camouflage

Adversarial Camouflage - Hiding Physical-World Attacks with Natural Styles.

Link

Perceptual Similarity

The unreasonable effectiveness of deep features as a perceptual metric.

Link

The CW Attack Algorithm

The Carlini & Wagner attack is currently one of the best known algorithms to generate adversarial examples.

Link

Norm: A Brief Introduction to the "Size" of Vectors in Machine Learning

Vector Norms in Machine Learning

Link