Neither Adversarial Training Nor Purification: Emergent Adversarial Robustness from Oscillatory Predictive Learning

2026-09-08

AI Summary

该研究提出了一种名为振荡预测学习（OPL）的方法，通过结合人工库拉莫托振荡神经元与自监督预训练来实现对抗鲁棒性，无需额外的对抗训练或净化步骤。

Abstract

Adversarial robustness in computer vision is still largely achieved through adversarial training or test-time adversarial purification, both of which introduce significant computational overhead by generating adversarial examples during training or performing iterative denoising at test time. We study whether empirical robustness can instead emerge from architectural and representation-learning inductive biases. We introduce Oscillatory Predictive Learning (OPL), a two-stage framework that combines Artificial Kuramoto Oscillatory Neurons (AKOrN) with predictive self-supervised pretraining using X-PhiNet. Because our default checkpoint uses randomized initial oscillator states, we compare it with other randomized adversarial defense methods that provide precise, reproducible, and strong attack protocols. Experiments on CIFAR-10 and CIFAR-100, with additional corruption evaluation on CIFAR-10-C, demonstrate that our method achieves competitive results under the AutoAttack-rand evaluation protocol. On CIFAR-10 and CIFAR-100, OPL attains 76.63$\pm$0.76$\%$ and 50.44$\%$ robust accuracy, respectively, under $\ell_\infty$, $\epsilon=8/255$, AutoAttack-rand with EoT $K=20$.

Problem

• Adversarial Robustness
• Computational Overhead
• Inductive Biases

Innovation

• Oscillatory Predictive Learning
• Artificial Kuramoto Oscillatory Neurons
• predictive self-supervised pretraining
• adversarial robustness