adversarial-ml
2 posts
Article
MITRE already filed your detection bypass as AML.T0015
ML malware detection is a deterministic classifier with a mappable decision boundary. Attackers exploit its learned bias. That demands more engineering.
Article
OpenCV 5.0 made adversarial perturbations transferable
OpenCV 5's bit-exact numerics and expanded encoder control shrink the attacker's modelling error against deepfake detectors. The exposure is structural.