Securing Brain-to-Brain Communication Channels Using Adversarial Training on SSVEP EEG
In this study, we investigate the effects of Adversarial Neural Network Training (ANNT) on the robustness and effectiveness of Brain-to-Brain Communication (B2B-C) systems using Steady-State Visually Evoked Potentials (SSVEP) EEG data. We utilized a combined Convolutional Neural Network-Temporal Con...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10847297/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583970021179392 |
|---|---|
| author | Hossein Ahmadi Ali Kuhestani Mohammadreza Keshavarzi Luca Mesin |
| author_facet | Hossein Ahmadi Ali Kuhestani Mohammadreza Keshavarzi Luca Mesin |
| author_sort | Hossein Ahmadi |
| collection | DOAJ |
| description | In this study, we investigate the effects of Adversarial Neural Network Training (ANNT) on the robustness and effectiveness of Brain-to-Brain Communication (B2B-C) systems using Steady-State Visually Evoked Potentials (SSVEP) EEG data. We utilized a combined Convolutional Neural Network-Temporal Convolutional Network (CNN-TCN) architecture to classify the data and assessed the system’s resistance to various adversarial strategies, including Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), Basic Iterative Method (BIM), Carlini & Wagner (C&W), and Momentum Iterative Method (MIM). By analyzing publicly accessible datasets, specifically Lee2019_SSVEP and Nakanishi2015, we observed significant enhancements in both accuracy and AUC metrics when ANNT was applied. Specifically, the Lee2019_SSVEP dataset exhibited a 24% increase in accuracy and a 0.23-point improvement in AUC, while the Nakanishi2015 dataset demonstrated improvements of 9% and 0.07 points, respectively. Our results indicate that PGD posed the greatest challenge to the model, significantly reducing accuracy and AUC across various scenarios, whereas FGSM was the least impactful. These findings highlight ANNT’s potential in fortifying the security and stability of B2B-C systems against diverse adversarial conditions. |
| format | Article |
| id | doaj-art-402038e41c6c4fb3b28667ebdbed03df |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-402038e41c6c4fb3b28667ebdbed03df2025-01-28T00:01:20ZengIEEEIEEE Access2169-35362025-01-0113143581437810.1109/ACCESS.2025.352877010847297Securing Brain-to-Brain Communication Channels Using Adversarial Training on SSVEP EEGHossein Ahmadi0https://orcid.org/0000-0002-3650-0280Ali Kuhestani1https://orcid.org/0000-0003-0725-3230Mohammadreza Keshavarzi2Luca Mesin3https://orcid.org/0000-0002-8239-2348Department of Electronics and Telecommunications, Mathematical Biology and Physiology, Politecnico di Torino, Turin, ItalyCommunications and Electronics Department, Faculty of Electrical and Computer Engineering, Qom University of Technology, Qom, IranIran Telecommunication Research Center (ITRC), Tehran, IranDepartment of Electronics and Telecommunications, Mathematical Biology and Physiology, Politecnico di Torino, Turin, ItalyIn this study, we investigate the effects of Adversarial Neural Network Training (ANNT) on the robustness and effectiveness of Brain-to-Brain Communication (B2B-C) systems using Steady-State Visually Evoked Potentials (SSVEP) EEG data. We utilized a combined Convolutional Neural Network-Temporal Convolutional Network (CNN-TCN) architecture to classify the data and assessed the system’s resistance to various adversarial strategies, including Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), Basic Iterative Method (BIM), Carlini & Wagner (C&W), and Momentum Iterative Method (MIM). By analyzing publicly accessible datasets, specifically Lee2019_SSVEP and Nakanishi2015, we observed significant enhancements in both accuracy and AUC metrics when ANNT was applied. Specifically, the Lee2019_SSVEP dataset exhibited a 24% increase in accuracy and a 0.23-point improvement in AUC, while the Nakanishi2015 dataset demonstrated improvements of 9% and 0.07 points, respectively. Our results indicate that PGD posed the greatest challenge to the model, significantly reducing accuracy and AUC across various scenarios, whereas FGSM was the least impactful. These findings highlight ANNT’s potential in fortifying the security and stability of B2B-C systems against diverse adversarial conditions.https://ieeexplore.ieee.org/document/10847297/Adversarial neural network trainingbrain-to-brain communicationelectroencephalogramadversarial attacksneuro-engineeringsecurity enhancement |
| spellingShingle | Hossein Ahmadi Ali Kuhestani Mohammadreza Keshavarzi Luca Mesin Securing Brain-to-Brain Communication Channels Using Adversarial Training on SSVEP EEG IEEE Access Adversarial neural network training brain-to-brain communication electroencephalogram adversarial attacks neuro-engineering security enhancement |
| title | Securing Brain-to-Brain Communication Channels Using Adversarial Training on SSVEP EEG |
| title_full | Securing Brain-to-Brain Communication Channels Using Adversarial Training on SSVEP EEG |
| title_fullStr | Securing Brain-to-Brain Communication Channels Using Adversarial Training on SSVEP EEG |
| title_full_unstemmed | Securing Brain-to-Brain Communication Channels Using Adversarial Training on SSVEP EEG |
| title_short | Securing Brain-to-Brain Communication Channels Using Adversarial Training on SSVEP EEG |
| title_sort | securing brain to brain communication channels using adversarial training on ssvep eeg |
| topic | Adversarial neural network training brain-to-brain communication electroencephalogram adversarial attacks neuro-engineering security enhancement |
| url | https://ieeexplore.ieee.org/document/10847297/ |
| work_keys_str_mv | AT hosseinahmadi securingbraintobraincommunicationchannelsusingadversarialtrainingonssvepeeg AT alikuhestani securingbraintobraincommunicationchannelsusingadversarialtrainingonssvepeeg AT mohammadrezakeshavarzi securingbraintobraincommunicationchannelsusingadversarialtrainingonssvepeeg AT lucamesin securingbraintobraincommunicationchannelsusingadversarialtrainingonssvepeeg |