Adversarial Attacks Neutralization via Data Set Randomization. (arXiv:2306.12161v1 [cs.LG])

Adversarial attacks on deep-learning models pose a serious threat to their
reliability and security. Existing defense mechanisms are narrow addressing a
specific type of attack or being vulnerable to sophisticated attacks. We
propose a new defense mechanism that, while being focused on image-based
classifiers, is general with respect to the cited category. It is rooted on
hyperspace projection. In particular, our solution provides a pseudo-random
projection of the original dataset into a new dataset. The proposed defense
mechanism creates a …

adversarial adversarial attacks attack attacks data defense general randomization reliability respect security serious threat vulnerable