SEP 8, 2026 · PREPRINT
Neither Adversarial Training Nor Purification: Emergent Adversarial Robustness from Oscillatory Predictive Learning
arXiv
This is an unrefereed preprint introducing a novel architecture (OPL with AKOrN) and reporting adversarial robustness results on standard benchmarks; the work is technically sound but lacks peer review and independent validation.
Reported
Robust accuracy CIFAR-1076.63±0.76%
Robust accuracy CIFAR-10050.44%
Attack threat modelℓ∞, ε=8/255