Generative Model

Generative Perturbation Network for Universal Adversarial Attacks on Brain-Computer Interfaces
This paper introduces the generative perturbation network (GPN), an efficient model for generating universal adversarial examples in EEG-based brain-computer interface (BCI) systems. GPN can produce perturbations capable of fooling deep neural networks with minor undetectable changes, and it outperforms previous methods in crafting signal-agnostic perturbations. Additionally, GPN can efficiently generate perturbations for various targets and victim models, demonstrating high transferability across classification networks.
Jiyoung Jung, HeeJoon Moon, Geunhyeok Yu, Hyoseok Hwang
PDF Cite Code DOI
Generative Perturbation Network for Universal Adversarial Attacks on Brain-Computer Interfaces