04:00
2026-08-24
arxiv.org
artificial-intelligence
Faults That Fortify: CNN Adversarial Robustness via GPU Undervolting
Researchers at an undisclosed institution found that undervolting GPUs during CNN training improves adversarial robustness while cutting energy use. In tests on MNIST and CIFAR-10 with LeNet, VGG-6, a…