Realizable Universal Adversarial Perturbations for Malware

no code implementations • 12 Feb 2021 • Raphael Labaca-Castro, Luis Muñoz-González, Feargus Pendlebury, Gabi Dreo Rodosek, Fabio Pierazzi, Lorenzo Cavallaro

Universal Adversarial Perturbations (UAPs), which identify noisy patterns that generalize across the input space, allow the attacker to greatly scale up the generation of such examples.

Malware Classification