Edathil Veedu, Arun (2024) Integrating Tensor-Based Data Representation and CNN to Detect and Mitigate Noise-Based Attacks on EEG Signals in BCI Systems. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (890kB) | Preview |
Preview |
PDF (Configuration Manual)
Download (752kB) | Preview |
Abstract
This research report represents a novel framework to integrate Tensor-Based Data encryption and Convolutional Neural Network Algorithms to enhance the detection and mitigation of noise-based data manipulation attacks on electroencephalography (EEG) signals within Brain-Computer Interface (BCI) systems. BCI is an evolving technology where several fields, such as the healthcare industry, entertainment, research, etc., rely on this to assist individuals who have mental or motion disorders. So, this situation necessitates robust security measures against various vulnerabilities, especially noise-based attacks that can compromise the integrity of neural data. This study identifies the gaps in existing detection and mitigation strategies for protecting EEG data from specific types of attacks. The primary research question analyses the impact of noise-based data manipulation attacks and develops an effective model for the integration of machine learning algorithms, such as the Convolutional Neural Network algorithm, with Tensor-Based Data Representation techniques. The primary objective of the proposed model is to produce a comprehensive solution for detecting and mitigating noise-based attacks. This model succeeded on implementing Tensor-Based Encryption and evaluating its effectiveness by simulating three types of ciphertext attacks. Two out of three attacks were failures, and one of them was partially successful. Additionally, the proposed model with CNN showed 97.4025% of detection rate, which is a higher detection rate in a complex brain related signal. However, more advanced version of tensors should be implemented with help of various libraries to prevent all types of ciphertext attacks and integrate advanced ML algorithm with more accuracy in detection.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email McLaughlin, Eugene UNSPECIFIED |
Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
Divisions: | School of Computing > Master of Science in Cyber Security |
Depositing User: | Ciara O'Brien |
Date Deposited: | 29 Jul 2025 11:49 |
Last Modified: | 29 Jul 2025 11:49 |
URI: | https://norma.ncirl.ie/id/eprint/8307 |
Actions (login required)
![]() |
View Item |