Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.10021 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929403214168064 |
|---|---|
| author | Yi, Hangjie Ming, Yuhang Liu, Dongjun Kong, Wanzeng |
| author_facet | Yi, Hangjie Ming, Yuhang Liu, Dongjun Kong, Wanzeng |
| contents | 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 but also benefits from the imperceptibility inherent in frequency-domain attack, achieving a better balance between attack performance and imperceptibility. Extensive experiments are conducted in both white- and grey-box scenarios and the results demonstrate that our attack method achieves state-of-the-art attack performance on three datasets and three deep-learning models. In the meanwhile, the perturbations in the signals attacked by our method are barely perceptible to the human visual system. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_10021 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Time-Frequency Jointed Imperceptible Adversarial Attack to Brainprint Recognition with Deep Learning Models Yi, Hangjie Ming, Yuhang Liu, Dongjun Kong, Wanzeng Cryptography and Security 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 but also benefits from the imperceptibility inherent in frequency-domain attack, achieving a better balance between attack performance and imperceptibility. Extensive experiments are conducted in both white- and grey-box scenarios and the results demonstrate that our attack method achieves state-of-the-art attack performance on three datasets and three deep-learning models. In the meanwhile, the perturbations in the signals attacked by our method are barely perceptible to the human visual system. |
| title | Time-Frequency Jointed Imperceptible Adversarial Attack to Brainprint Recognition with Deep Learning Models |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2403.10021 |