Smart Defense: AI-Powered Adaptive IDs for Real-Time Zero-Day Threat Mitigation

References

[1] Bilge, L., & Dumitras, T. (2012). Before we knew it: An empirical study of zero-day attacks in the real world. ACM Conference on Computer and Communications Security. https://doi.org/10.1145/2382196.2382261

[2] Scarfone, K., & Mell, P. (2007). Guide to Intrusion Detection and Prevention Systems (IDPS). NIST Special Publication 800-94.

[3] Sommer, R., & Paxson, V. (2010). Outside the closed world: On using machine learning for network intrusion detection. IEEE Symposium on Security and Privacy. https://doi.org/10.1109/SP.2010.40

[4] Kim, G., Lee, S., & Kim, S. (2016). A novel hybrid intrusion detection method integrating anomaly detection with misuse detection. Expert Systems with Applications, 41(4), 1690–1700. https://doi.org/10.1016/j.eswa.2013.08.066

[5] Vinayakumar, R., Soman, K. P., & Poornachandran, P. (2019). Evaluating deep learning approaches to characterize and classify network traffic. Journal of Intelligent & Fuzzy Systems, 36(5), 4743–4751. https://doi.org/10.3233/JIFS-181574

[6] AlSkaif, T., Lampropoulos, I., van den Broek, M., & van Sark, W. (2020). A self-learning approach for detection and classification of anomalies in PV systems. Renewable Energy, 145, 1675–1685. https://doi.org/10.1016/j.renene.2019.06.108

[7] Khan, M. A., Nam, Y., & Kim, H. (2021). Machine learning-based distributed intrusion detection systems: A survey. Journal of Network and Computer Applications, 180, 103020. https://doi.org/10.1016/j.jnca.2021.103020

[8] Garcia-Teodoro, P., Diaz-Verdejo, J., Macia-Fernandez, G., & Vazquez, E. (2009). Anomaly-based network intrusion detection: Techniques, systems and challenges. Computers & Security, 28(1-2), 18–28. https://doi.org/10.1016/j.cose.2008.08.003

[9] Patcha, A., & Park, J. M. (2007). An overview of anomaly detection techniques: Existing solutions and latest technological trends. Computer Networks, 51(12), 3448–3470. https://doi.org/10.1016/j.comnet.2006.11.001

[10] Xia, Y., Wang, X., Zhang, C., & Deng, K. (2018). A novel hybrid model based on LSTM and CNN for intrusion detection. EURASIP Journal on Wireless Communications and Networking, 2018(1), 1–11. https://doi.org/10.1186/s13638-018-1345-4

[11] Yin, C., Zhu, Y., Fei, J., & He, X. (2017). A deep learning approach for intrusion detection using recurrent neural networks. IEEE Access, 5, 21954–21961. https://doi.org/10.1109/ACCESS.2017.2762418

[12] Parisi, G. I., Kemker, R., Part, J. L., Kanan, C., & Wermter, S. (2019). Continual lifelong learning with neural networks: A review. Neural Networks, 113, 54–71. https://doi.org/10.1016/j.neunet.2019.01.012

[13] Lyu, L., Yu, H., & Yang, Q. (2020). Threats to federated learning: A survey. arXiv preprint arXiv:2003.02133.

[14] Sharafaldin, I., Lashkari, A. H., & Ghorbani, A. A. (2018). Toward generating a new intrusion detection dataset and intrusion traffic characterization. ICISSP, 108–116. https://doi.org/10.5220/0006639801080116

[15] Garcia-Teodoro, P., Diaz-Verdejo, J., Macia-Fernandez, G., & Vazquez, E. (2009). Anomaly-based network intrusion detection: Techniques, systems and challenges. Computers & Security, 28(1-2), 18–28. https://doi.org/10.1016/j.cose.2008.08.003

[16] Hodo, E., Bellekens, X., Hamilton, A., Dubouilh, P. L., Iorkyase, E., Tachtatzis, C., & Atkinson, R. (2016). Threat detection for the Internet of Things using neural network ensemble. 2016 International Symposium on Networks, Computers and Communications (ISNCC), 1–6. https://doi.org/10.1109/ISNCC.2016.7746067

[17] Kim, G., Lee, S., & Kim, S. (2014). A novel hybrid intrusion detection method integrating anomaly detection with misuse detection. Expert Systems with Applications, 41(4), 1690–1700. https://doi.org/10.1016/j.eswa.2013.08.066

[18] Patcha, A., & Park, J. M. (2007). An overview of anomaly detection techniques: Existing solutions and latest technological trends. Computer Networks, 51(12), 3448–3470. https://doi.org/10.1016/j.comnet.2006.09.001

[19] Sommer, R., & Paxson, V. (2010). Outside the closed world: On using machine learning for network intrusion detection. 2010 IEEE Symposium on Security and Privacy, 305–316. https://doi.org/10.1109/SP.2010.25

[20] Zhou, C., & Paffenroth, R. C. (2017). Anomaly detection with robust deep autoencoders. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 665–674. https://doi.org/10.1145/3097983.3098052

@article{1708240,
      author = {Mohammad Majharul Islam Jabed, Amit Banwari Gupta, Sharmin Akter, Muntaha Islam, Jannatul Ferdous},
      title = {Smart Defense: AI-Powered Adaptive IDs for Real-Time Zero-Day Threat Mitigation},
      journal = {Iconic Research And Engineering Journals},
      year = {2023},
      volume = {7},
      number = {3},
      pages = {804-815},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1708240.pdf},
      abstract = {Zero-day attacks have become a permanent threat to digital security systems worldwide because of continuous digital progress. Traditional intrusion detection systems (IDS) cannot detect previously unknown vulnerabilities and subsequent mitigation because their static rule-based detection systems fall short. The proposed research presents an innovative AI-based adaptive IDS framework that soldiers to target zero-day threats during real-time operations. The proposed system uses CNN, LSTM deep learning, and machine learning algorithms to detect unusual behaviors that warrant threat identification, although signature-based data is unavailable. The model received evaluation using benchmark sets consisting of NSL-KDD and CICIDS2017 while processing diverse attack patterns and standard network operations. The system implements a threat detection strategy update mechanism through continual learning methods, ensuring its ability to adapt as the threat ecosystem changes. The proposed IDS achieves superior results against conventional models by maintaining very high accuracy (97.4%) and precision (95.8%) in addition to recall (96.9%) and F1-Score (96.3%) and low false-positive rates. Real-time monitoring will not strain system infrastructure because the architecture has optimized resource utilization. Table, bar graphs, and pie charts present the analytical summary of threat recognition features, resource needs, and threat distribution types. The adaptive model design both improves quick response and decreases the need for human interaction. The research enhances existing studies about intelligent cybersecurity protections and provides applicable solutions for establishing security in public institutions, healthcare centers, and financial networks. The future development will combine blockchain authentication with federated learning protocols for protecting privacy during threat intelligence exchange. Artificial intelligence systems that learn and adapt form a significant paradigm shift toward advanced protection mechanisms that can prevent new zero-day attacks.},
      keywords = {Intrusion Detection System, Zero-Day Attack, Artificial Intelligence, Cybersecurity, Real-Time Threat Detection},
      month = {September},
  }