Neither Adversarial Training Nor Purification: Emergent Adversarial Robustness from Oscillatory Predictive Learning
This work introduces Oscillatory Predictive Learning (OPL), a two-stage framework that combines Artificial Kuramoto Oscillatory Neurons (AKOrN) with predictive self-supervised pretraining using X-PhiNet and compares it with other randomized adversarial defense methods that provide precise, reproducible, and strong atta...
M. Habibi, Klea Ziu, Martin Takác et al.
· 0 citations