Survival of the Cheapest: Cost-Aware Hardware Adaptation for Adversarial Robustness

ArXi:2409.07609v2 Announce Type: replace-cross Deploying adversarially robust machine learning systems requires continuous trade-offs between robustness, cost, and latency. We present an autonomic decision- framework providing a quantitative foundation for adaptive hardware selection and hyper-parameter tuning in cloud-native deep learning. The framework applies accelerated failure time (AFT) models to quantify the effect of hardware choice, batch size, epochs, and validation accuracy on model survival time.