International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | AI Based Cybersecurity Threat Detection Device |
|---|---|
| ABSTRACT | In this work, several machine learning classifiers were evaluated for cybersecurity threat detection, including Decision Tree, Boosted Tree, Logistic Regression Tree, and Support Vector Machine (SVM). Each model was trained and validated in MATLAB using a cyber threat data to identify the most efficient algorithm for real-time deployment. While Boosted Trees and SVM demonstrated strong predictive performance, they required higher computational resources, making them less suitable for embedded environments. Logistic Regression Trees offered reliable binary classification but showed reduced accuracy for complex threat patterns. Considering portability, execution speed, interpretability, and accuracy requirements, the Decision Tree model was selected for implementation on Raspberry Pi. The model enables real-time threat prediction, and results are displayed on an LCD with an audible buzzer alert for detected threats, making the device a low-cost and hardware-integrated cybersecurity solution. |
| AUTHOR | SNEHA S N, SNEHA YERI, TRISHA H R, VAISHNAVI K Y, DR MALATESH SH Student, Dept. of Computer Science and Engineering, MS Engineering College, Bengaluru, Karnataka, India HOD, Dept. of Computer Science and Engineering, MS Engineering College, Bengaluru, Karnataka, India |
| VOLUME | 180 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1401028 |
| pdf/28_AI Based Cybersecurity Threat Detection Device.pdf | |
| KEYWORDS | |
| References | [1] "A Machine Learning Approach to Cybersecurity Threat Detection" by J. Kim et al. (IEEE, 2020). [2] "Raspberry Pi-Based Network Intrusion Detection System" by M. A. Al-Amin et al. (IJCSIT, 2019). [3] "IP Address Classification Using Machine Learning" by S. Kumar et al. (IJCNIS, 2020). [4] "Anomaly-Based Intrusion Detection System Using Machine Learning" by A. L. Buczak et al. (IEEE, 2016). [5] "Cybersecurity Threat Detection Using Deep Learning" by Y. Xin et al. (IEEE, 2018). [6] "A Survey on Cybersecurity Threat Detection Using Machine Learning" by R. Vinayakumar et al. (IEEE, 2019). [7] "Real-Time Network Intrusion Detection System Using Raspberry Pi" by S. S. Patil et al. (IJERT, 2020). [8] “IP Address-Based Threat Detection Using Machine Learning" by A. K. Jain et al. (IJCNIS, 2020). [9] “Cybersecurity Threat Detection Using Convolutional Neural Networks" by Y. Liu et al. (IEEE, 2020). [10] “Anomaly-Based Cybersecurity Threat Detection Using Machine Learning" by M. A. Ferrag et al. (IEEE, 2020). |
