NeuroscienceIEEE Transactions on Neural Systems and Rehabilitation EngineeringPeer-reviewed
Synthetic EMG Based on Adversarial Style Transfer can Effectively Attack Biometric-based Personal Identification Models
Peiqi Kang, Shuo Jiang, Peter Bradley Shull
This paper demonstrates that synthetic EMG signals generated via adversarial style transfer can effectively attack biometric identification models, achieving high success rates in confusing and manipulating them.