AI RESEARCH
NERO-Net: A Neuroevolutionary Approach for the Design of Adversarially Robust CNNs
arXiv CS.AI
•
ArXi:2603.25517v1 Announce Type: cross Neuroevolution automates the complex task of neural network design but often ignores the inherent adversarial fragility of evolved models which is a barrier to adoption in safety-critical scenarios. While robust