SupplementaryMaterial: TowardEfficientRobust Trainingagainst UnionofℓpThreatModels
–Neural Information Processing Systems
For this, we utilize an implementationbyCroceandHein[2021],togetherwithlinearscaling(=10)ofthegradientinorder to balance the relative scale to random noise.
Neural Information Processing Systems
Feb-11-2026, 04:12:11 GMT