Enhancement Of Intrusion Detection System In Explainable Artificial Intelligence
DOI:
https://doi.org/10.29284/e90frk79Keywords:
Intrusion Detection System, Explainable AI, CatBoost, SHAP, MLP.Abstract
Intrusion Detection Systems (IDS) remain vital to the security of contemporary networks; however, conventional techniques find it difficult to combat progressively sophisticated cyber-attacks. In order to overcome such difficulty, XAI has become the approach of choice by which the issues of transparency and trust in automated threat detection are solved. The present work introduces a conceptualization of XAI-based IDS, coupling various machine learning classifiers with SHAP and LIME to generate unambiguous, human-readable rationale for every inference. It has methodology such as dataset preprocessing, RFE and correlation analysis based feature selection and CatBoost, MLP and Gaussian Naïve Bayes based model development. XAI methods are used to find out the most significant contributing features and clarify the ways of attack detection on the class-based level. The issue that the presented work is focused on is the lack of interpretability of high-performance IDS models, which restricts their application in the real world. The suggested solution would improve transparency, yet it is very accurate, which allows optimists to have confidence in, authenticate, and refine model choices. Experimentation indicates that CatBoost has validation accuracy of around 97 per cent with almost perfect model accuracy and recall on key attack types. MLP does the same, that is, the SHAP analysis underlines the strongest influential features that make predictions. On balance, the XAI-enhanced IDS are much better in terms of its detection performance as well as interpretability.
References
1. Wang, Maonan, Kangfeng Zheng, Yanqing Yang, and Xiujuan Wang. "An explainable machine learning framework for intrusion detection systems." IEEE Access 8 (2020): 73127-73141.
2. Vigneswaran, Rahul K., R. Vinayakumar, K. P. Soman, and Prabaharan Poornachandran. "Evaluating shallow and deep neural networks for network intrusion detection systems in cyber security." In 2018 9th International conference on computing, communication and networking technologies (ICCCNT), pp. 1-6. IEEE, 2018.
3. Patil, Shruti, Vijayakumar Varadarajan, Siddiqui Mohd Mazhar, Abdulwodood Sahibzada, Nihal Ahmed, Onkar Sinha, Satish Kumar, Kailash Shaw, and Ketan Kotecha. "Explainable artificial intelligence for intrusion detection system." Electronics 11, no. 19 (2022): 3079.
4. Mohale, Vincent Zibi, and Ibidun Christiana Obagbuwa. "A systematic review on the integration of explainable artificial intelligence in intrusion detection systems to enhance transparency and interpretability in cybersecurity." Frontiers in Artificial Intelligence 8 (2025): 1526221.
5. Birahim, Shaikh Afnan, Avijit Paul, Fahmida Rahman, Yamina Islam, Tonmoy Roy, Mohammad Asif Hasan, Fariha Haque, and Muhammad EH Chowdhury. "Intrusion detection for wireless sensor network using particle swarm optimization based explainable ensemble machine learning approach." IEEE Access (2025).
6. Ahsan, Shakil Ibne, Phil Legg, and SM Iftekharul Alam. "An explainable ensemble-based intrusion detection system for software-defined vehicle ad-hoc networks." Cyber Security and Applications 3 (2025): 100090.
7. Zhang, Hangsheng, Dongqi Han, Shangyuan Zhuang, Zhiliang Wang, Jiyan Sun, Yinlong Liu, Jiqiang Liu, and Jinsong Dong. "Explainable and transferable adversarial attack for ml-based network intrusion detectors." IEEE Transactions on Dependable and Secure Computing (2025).
8. Ali, Daim, Muhammad Kamran Abid, Muhammad Baqer, Yasir Aziz, Naeem Aslam, and Nasir Umer. "IMPROVING THE EXPLAINABILITY AND TRANSPARENCY OF DEEP LEARNING MODELS IN INTRUSION DETECTION SYSTEMS." Kashf Journal of Multidisciplinary Research 2, no. 02 (2025): 149-164.
9. Rane, J., S. K. Mallick, O. Kaya, and N. L. Rane. "Enhancing black-box models: advances in explainable artificial intelligence for ethical decision-making." Future Research Opportunities for Artificial Intelligence in Industry 4 (2024): 136-180.
10. Shen, Max W. "Trust in AI: Interpretability is not necessary or sufficient, while black-box interaction is necessary and sufficient." arXiv preprint arXiv:2202.05302 (2022).
11. Al-Janabi, Mohammed, Mohd Arfian Ismail, and Ahmed Hussein Ali. "Intrusion Detection Systems, Issues, Challenges, and Needs." Int. J. Comput. Intell. Syst. 14, no. 1 (2021): 560-571.
12. Kalasampath, Khushi, K. N. Spoorthi, Sreeparvathy Sajeev, Sahil Sarma Kuppa, Kavya Ajay, and M. Angulakshmi. "A Literature review on applications of explainable artificial intelligence (XAI)." IEEE Access (2025).
13. Lundberg, Scott M., and Su-In Lee. "A unified approach to interpreting model predictions." Advances in neural information processing systems 30 (2017).
14. Muhammad, Aoun E., Kin-Choong Yow, Nebojsa Bacanin-Dzakula, and Muhammad Attique Khan. "L-XAIDS: A LIME-based eXplainable AI framework for Intrusion Detection Systems." arXiv preprint arXiv:2508.17244 (2025).
15. Manthena, Harikha, Shaghayegh Shajarian, Jeffrey Kimmell, Mahmoud Abdelsalam, Sajad Khorsandroo, and Maanak Gupta. "Explainable artificial intelligence (xai) for malware analysis: A survey of techniques, applications, and open challenges." IEEE Access (2025).
16. Fiok, Krzysztof, Farzad V. Farahani, Waldemar Karwowski, and Tareq Ahram. "Explainable artificial intelligence for education and training." The Journal of Defense Modeling and Simulation 19, no. 2 (2022): 133-144.
17. Nazat, Sazid, Lingxi Li, and Mustafa Abdallah. "XAI-ADS: An explainable artificial intelligence framework for enhancing anomaly detection in autonomous driving systems." Ieee Access 12 (2024): 48583-48607.
18. Senevirathna, Thulitha, Bartlomiej Siniarski, Madhusanka Liyanage, and Shen Wang. "Deceiving post-hoc explainable ai (xai) methods in network intrusion detection." In 2024 IEEE 21st Consumer Communications & Networking Conference (CCNC), pp. 107-112. IEEE, 2024.
19. Muneer, Salman, Umer Farooq, Atifa Athar, Muhammad Ahsan Raza, Taher M. Ghazal, and Shadman Sakib. "A critical review of artificial intelligence based approaches in intrusion detection: A comprehensive analysis." Journal of Engineering 2024, no. 1 (2024): 3909173.
20. Wali, Syed, Yasir Ali Farrukh, and Irfan Khan. "Explainable AI and random forest based reliable intrusion detection system." Computers & Security (2025): 104542.
21. Alabbadi, Adel, and Fuad Bajaber. "An Intrusion Detection System over the IoT Data Streams Using eXplainable Artificial Intelligence (XAI)." Sensors (Basel, Switzerland) 25, no. 3 (2025): 847.
22. Mahmoud, Maiada M., Yasser Omar Youssef, and Ayman A. Abdel-Hamid. "XI2s-IDS: An explainable intelligent 2-stage intrusion detection system." Future Internet 17, no. 1 (2025): 25.
23. Almolhis, Nawaf Abdualaziz. "Intrusion Detection Using Hybrid Random Forest and Attention Models and Explainable AI Visualization." Journal of Internet Services and Information Security 15, no. 1 (2025): 371-384.
24. Arreche, Osvaldo, Tanish R. Guntur, Jack W. Roberts, and Mustafa Abdallah. "E-xai: Evaluating black-box explainable ai frameworks for network intrusion detection." IEEE Access 12 (2024): 23954-23988.
25. Hooshmand, Mohammad Kazim, Manjaiah Doddaghatta Huchaiah, Ahmad Reda Alzighaibi, Hasan Hashim, El-Sayed Atlam, and Ibrahim Gad. "Robust network anomaly detection using ensemble learning approach and explainable artificial intelligence (XAI)." Alexandria Engineering Journal 94 (2024): 120-130.
26. Gaspar, Diogo, Paulo Silva, and Catarina Silva. "Explainable AI for intrusion detection systems: LIME and SHAP applicability on multi-layer perceptron." IEEE Access 12 (2024): 30164-30175.
27. Corea, Pap M., Yongxin Liu, Jian Wang, Shuteng Niu, and Houbing Song. "Explainable ai for comparative analysis of intrusion detection models." In 2024 IEEE International Mediterranean Conference on Communications and Networking (MeditCom), pp. 585-590. IEEE, 2024.
28. Nwakanma, Cosmas Ifeanyi, Love Allen Chijioke Ahakonye, Judith Nkechinyere Njoku, Jacinta Chioma Odirichukwu, Stanley Adiele Okolie, Chinebuli Uzondu, Christiana Chidimma Ndubuisi Nweke, and Dong-Seong Kim. "Explainable artificial intelligence (XAI) for intrusion detection and mitigation in intelligent connected vehicles: A review." Applied Sciences 13, no. 3 (2023): 1252.
29. Sivamohan, Sivanandam, and S. S. Sridhar. "An optimized model for network intrusion detection systems in industry 4.0 using XAI based Bi-LSTM framework." Neural Computing and Applications 35, no. 15 (2023): 11459-11475.
30. Wardhani, Rini Wisnu, Dedy Septono Catur Putranto, Uk Jo, and Howon Kim. "Toward enhanced attack detection and explanation in intrusion detection system-based IoT environment data." IEEE Access 11 (2023): 131661-131676.
31. Bauskar, Sanjay. "Enhancing Cybersecurity In Network Intrusion Detection System Based On Artificial Intelligence (AI) Techniques." Available at SSRN 4987362 (2023).
32. https://data.mendeley.com/datasets/29hdbdzx2r/1
33. Mohammed, Abdulrahman Jassam, Muhanad Hameed Arif, and Ali Adil Ali. "A multilayer perceptron artificial neural network approach for improving the accuracy of intrusion detection systems." IAES International Journal of Artificial Intelligence 9, no. 4 (2020): 609.
34. Mahmod, Mahmod S., Zakaria A. Hamed Alnaish, and Ismail Ahmed A. Al-Hadi. "Hybrid intrusion detection system using artificial bee colony algorithm and multi-layer perceptron." International Journal of Computer Science and Information Security 13, no. 2 (2015): 1.
35. Esmaily, Jamal, Reza Moradinezhad, and Jamal Ghasemi. "Intrusion detection system based on multi-layer perceptron neural networks and decision tree." In 2015 7th Conference on Information and Knowledge Technology (IKT), pp. 1-5. IEEE, 2015.
36. Mahbooba, Basim, Mohan Timilsina, Radhya Sahal, and Martin Serrano. "Explainable artificial intelligence (XAI) to enhance trust management in intrusion detection systems using decision tree model." Complexity 2021, no. 1 (2021): 6634811.
37. Al-Naymat, Ghazi, Mouhammd Al-Kasassbeh, Nosaiba Abu-Samhadanh, and Sherif Sakr. "CLASSIFICATION OF VOIP AND NON-VOIP TRAFFIC USING MACHINE LEARNING APPROACHES." Journal of Theoretical & Applied Information Technology (2016).
38. Mutlu, Gökay, and Nese Rihani. "Intrusion Detection System with Explainable AI and Federated Learning."
39. Hajjouz, Abdulkader, and Elena Yurievna Avksentieva. "An approach to configuring CatBoost for advanced detection of DoS and DDoS attacks in network traffic." Вестник Астраханского государственного технического университета. Серия: Управление, вычислительная техника и информатика 3 (2024): 64-74.
40. Saleem, Moeed, Muhammad Azam, Zeeshan Mubeen, and Gohar Mumtaz. "Machine learning for improved threat detection: LightGBM vs. CatBoost." Journal of Computing & Biomedical Informatics 7, no. 01 (2024): 571-580.
41. Kaya, Kiymet, Elif Ak, Sumeyye Bas, Berk Canberk, and Sule Gunduz Oguducu. "X-CBA: Explainability aided CatBoosted Anomal-E for intrusion detection system." In ICC 2024-IEEE International Conference on Communications, pp. 2288-2293. IEEE, 2024.
42. Islam, Riadul, Maloy K. Devnath, Manar D. Samad, and Syed Md Jaffrey Al Kadry. "GGNB: Graph-based Gaussian naive Bayes intrusion detection system for CAN bus." Vehicular Communications 33 (2022): 100442.
43. Naiem, Sarah, Ayman E. Khedr, Amira M. Idrees, and Mohamed I. Marie. "Enhancing the efficiency of Gaussian Naïve Bayes machine learning classifier in the detection of DDOS in cloud computing." IEEE Access 11 (2023): 124597-124608.
44. Jafer, Shatha H. "Optimize network intrusion detection system based on PCA feature extraction and three naïve bayes classifiers." In Journal of Physics: Conference Series, vol. 2322, no. 1, p. 012092. IOP Publishing, 2022.
45. Rafin, Nafiz Imtiaz, Swattic Ghose, Ahsanul Islam, Fahim Ul Islam, Dr Md Golam Rabiul Alam, and Amitabha Chakrabarty. "Enhancing Intrusion Detection: A Robust Ensemble Learning Approach with Explainable AI and Strategic Fused Voting-Stacking Mechanism." In Proceedings of the 3rd International Conference on Computing Advancements, pp. 1050-1057. 2024.
46. Ribeiro, Marco Tulio, Sameer Singh, and Carlos Guestrin. "" Why should i trust you?" Explaining the predictions of any classifier." In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp. 1135-1144. 2016.
47. Lundberg, Scott M., and Su-In Lee. "A unified approach to interpreting model predictions." Advances in neural information processing systems 30 (2017).
48. Salih, Ahmed M., Zahra Raisi‐Estabragh, Ilaria Boscolo Galazzo, Petia Radeva, Steffen E. Petersen, Karim Lekadir, and Gloria Menegaz. "A perspective on explainable artificial intelligence methods: SHAP and LIME." Advanced Intelligent Systems 7, no. 1 (2025): 2400304.
49. Gaspar, Diogo, Paulo Silva, and Catarina Silva. "Explainable AI for intrusion detection systems: LIME and SHAP applicability on multi-layer perceptron." IEEE Access 12 (2024): 30164-30175.
50. Islam, Md Tohidul, Md Khalid Syfullah, Md Golam Rashed, and Dipankar Das. "Bridging the gap: advancing the transparency and trustworthiness of network intrusion detection with explainable AI." International Journal of Machine Learning and Cybernetics 15, no. 11 (2024): 5337-5360.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
