# ML

Extending FGSM to Other Norms

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

Posted November 20. 2020. 680 words. 3 min read.
Link

Adversarial Camouflage

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

Posted November 11. 2020. 374 words. 2 min read.
Link

Perceptual Similarity

The unreasonable effectiveness of deep features as a perceptual metric.

Posted November 1. 2020. 861 words. 4 min read.
Link

The CW Attack Algorithm

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

Posted October 25. 2020. 975 words. 5 min read.
Link

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

Vector Norms in Machine Learning

Posted October 6. 2020. 903 words. 4 min read.
Link