Time-Frequency Jointed Imperceptible Adversarial Attack to Brainprint Recognition with Deep Learning Models

arXiv:2403.10021v1 Announce Type: new
Abstract: EEG-based brainprint recognition with deep learning models has garnered much attention in biometric identification. Yet, studies have indicated vulnerability to adversarial attacks in deep learning models with EEG inputs. In this paper, we introduce a novel adversarial attack method that jointly attacks time-domain and frequency-domain EEG signals by employing wavelet transform. Different from most existing methods which only target time-domain EEG signals, our method not only takes advantage of the time-domain attack's potent adversarial strength …

adversarial adversarial attack adversarial attacks arxiv attack attacks attention biometric biometric identification cs.cr deep learning domain identification inputs novel recognition studies vulnerability