Vol 2 No 1 (March 2026)
Articles

AI in Cybersecurity: Ethical Challenges of AI-Based Intrusion Detection Systems: A Comparative Analysis of EU, U.S., and South Korea

PDF
  • rihab karoud
rihab karoud
cybersecurity

Published 01-09-2026

Keywords

  • artificial intelligence,
  • intrusion detection systems,
  • ethical challenges,
  • network activities,
  • cybersecurity

Copyright (c) 2026 rihab karoud (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Abstract

The concept of artificial intelligence (AI) has been increasingly used in the field of cybersecurity, especially in the development of intrusion detection systems (IDS). The conventional approach to developing intrusion detection systems involves the use of rule-based systems as well as signatures of attacks. However, this approach has been criticized for its inability to deal with emerging threats such as zero-day exploits. This has led to the development of intrusion detection systems that incorporate the concept of machine learning in the analysis of network activities. This approach has been effective in the detection of anomalies that could be indicative of malicious activities. However, the use of this approach in the development of intrusion detection systems has raised ethical issues. This paper seeks to discuss the ethical issues surrounding the application of AI-based intrusion detection systems by first presenting an overview of the technical basis of the systems and the technical benefits they offer. Secondly, the paper will discuss the ethical issues surrounding the application of the system. Some of the ethical issues discussed will include the lack of explainability of machine learning algorithms, the possibility of biased decision-making by the system, and the ethical issues surrounding the collection of large amounts of personal information. Additionally, the paper will discuss the technical solutions to the ethical issues surrounding the application of the system. Some of the technical solutions to the ethical issues will include the application of explainable AI, federated learning, differential privacy, and synthetic data. Lastly, the paper will discuss the regulatory frameworks adopted by the European Union, the US, and South Korea regarding the application of the system. The analysis identifies the gaps in the regulations as well as the technical limitations in the ethical use of AI-based IDS. The study offers recommendations to improve the design of AI-based IDS. The study emphasizes the need to strike a balance between the increasing technical capabilities of AI systems and the need to have proper ethical and regulatory checks in the use of AI in cybersecurity.

PDF

Downloads

Download data is not yet available.

References

  1. [1] Khan, M. I., Arif, A., & Khan, A. R. A. (2024). "The most recent advances and uses of AI in cybersecurity". BULLET: Jurnal Multidisiplin Ilmu, 3(4), 566–578. https://journal.mediapublikasi.id/index.php/bullet/article/view/4540.
  2. [2] Kim, A., Park, M., & Lee, D. H. (2020). AI-IDS: Application of deep learning to real-time web intrusion detection. IEEE Access, 8, 70245–70261 https://doi.org/10.1109/ACCESS.2020.2986882
  3. [3] Liu, Y., Liu, S., & Zhao, X. (2017). Intrusion detection algorithm based on convolutional neural network. Beijing Ligong Daxue Xuebao/Transactions of Beijing Institute of Technology, 37(12), 1271–1275. https://doi.org/10.15918/j.tbit1001-0645.2017.12.011
  4. [4] 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
  5. [5] Vinayakumar, R., Alazab, M., Soman, K. P., Poornachandran, P., Al-Nemrat, A., & Venkatraman, S. (2019). Deep learning approach for intelligent intrusion detection system. IEEE Access, 7, 41525–41550. https://doi.org/10.1109/ACCESS.2019.2895334
  6. [6] Chiba, Z., Abghour, N., Moussaid, K., El Omri, A., & Rida, M. (2019). Intelligent approach to build a deep neural network-based IDS for cloud environment using combination of machine learning algorithms. Computers & Security, 86, 291–317. https://doi.org/10.1016/j.cose.2019.06.009
  7. [7] Muneer, S., Farooq, U., Athar, A., Raza, M. A., Ghazal, T. M., & Sakib, S. (2024). A critical review of artificial intelligence based approaches in intrusion detection: A comprehensive analysis. Journal of Cybersecurity Research, 15 April. https://doi.org/10.1155/2024/3909173
  8. [8] Eskandari, M., Janjua, Z. H., Vecchio, M., & Antonelli, F. (2020). Passban IDS: An intelligent anomaly-based intrusion detection system for IoT edge devices. IEEE Internet of Things Journal, 7(8), 6882–6897. https://doi.org/10.1109/JIOT.2020.2970501
  9. [9] Gharaee, H., & Hosseinvand, H. (2016). A new feature selection IDS based on genetic algorithm and SVM. In 2016 8th International Symposium on Telecommunications (IST) (pp. 139–144). IEEE. https://doi.org/10.1109/ISTEL.2016.7881798
  10. [10] Santos, R. R. d., Viegas, E. K., Santin, A. O., & Cogo, V. V. (2023). Reinforcement learning for intrusion detection: More model longness and fewer updates. IEEE Transactions on Network and Service Management, 20(2), 2040–2055. https://doi.org/10.1109/TNSM.2022.3207094
  11. [11] Wassermann, S., Cuvelier, T., Mulinka, P., & Casas, P. (2021). Adaptive and reinforcement learning approaches for online network monitoring and analysis. IEEE Transactions on Network and Service Management, 18(2), 1832–1849. https://doi.org/10.1109/TNSM.2020.3037486
  12. [12] LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436–444. https://doi.org/10.1038/nature14539
  13. [13] Tomide, A., & Adelusi, J. (2025). Deep learning for intrusion detection: Challenges and opportunities. Journal of AI Security Research, 10(2), 45–62.
  14. [14] Chinnasamy, R., Subramanian, M., Easwaramoorthy, S. V., & Cho, J. (2025). Deep learning-driven methods for network-based intrusion detection systems: A systematic review. ICT Express, 11(1), 181–215. https://doi.org/10.1016/j.icte.2025.01.005
  15. [15] Fu, X., Zhou, N., Jiao, L., et al. (2021). The robust deep learning–based schemes for intrusion detection in Internet of Things environments. Annals of Telecommunications, 76, 273–285. https://doi.org/10.1007/s12243-021-00854-y
  16. [16] Mohale, V. Z., & Obagbuwa, I. C. (2025). Evaluating machine learning-based intrusion detection systems with explainable AI: Enhancing transparency and interpretability. Frontiers in Computer Science, 7, 1520741. https://doi.org/10.3389/fcomp.2025.1520741
  17. [17] Asharf, J., Moustafa, N., Khurshid, H., Debie, E., Haider, W., & Wahab, A. (2020). A review of intrusion detection systems using machine and deep learning in Internet of Things: Challenges, solutions and future directions. Electronics, 9, 1177. https://doi.org/10.3390/electronics9071177
  18. [18] Khatkar, M., Kumar, K., & Kumar, B. (2023). Design and analysis of intrusion detection system based on ensemble deep neural network and XAI. International Review of Modelling and Simulation, 16, 129. https://doi.org/10.15866/iremos.v16i3.23437
  19. [19] Balyan, A. K., Ahuja, S., Lilhore, U. K., Sharma, S. K., Manoharan, P., Algarni, A. D., et al. (2022). A hybrid intrusion detection model using EGAPSO and improved random forest method. Sensors, 22, 5986. https://doi.org/10.3390/s22165986.
  20. [20] Mynuddin, M., Khan, S. U., Chowdhury, Z., Islam, F., Islam, M., Hossain, M., et al. (2024). “Automatic network intrusion detection system using machine learning and deep learning”. [Preprint]. https://doi.org/10.36227/techrxiv.170792293.35058961/v1.
  21. [21] Barnard, P., DaSilva, L. A., & Marchetti, N. (2024). Don’t just explain, enhance! Using explainable artificial intelligence (XAI) to automatically improve network intrusion detection [Preprint]. arXiv. https://arxiv.org/abs/2407.17373.
  22. [22] Neupane, S., Ables, J., Anderson, W., Mittal, S., Rahimi, S., Banicescu, I., et al. (2022). Explainable intrusion detection systems (X-IDS): A survey of current methods, challenges, and opportunities. IEEE Access, 10, 112392–112415. https://doi.org/10.1109/ACCESS.2022.3216617.
  23. [23] Sevri, M., & Karacan, H. (2023). Explainable artificial intelligence (XAI) for deep learning-based intrusion detection systems. In 4th International Conference on Artificial Intelligence and Applied Mathematics in Engineering (pp. 39–55) https://doi.org/10.1007/978-3-031-31956-3_4.
  24. [24] Wang, L., Zhang, Y., & Li, H. (2024). Explainable AI-based innovative hybrid ensemble model for intrusion detection systems. Journal of Cloud Computing: Advances, Systems and Applications, 13, 71. https://doi.org/10.1186/s13677-024-00712-x.
  25. [25] Zhang, Y., Muniyandi, R. C., & Qamar, F. (2025). A review of deep learning applications in intrusion detection systems: Overcoming challenges in spatiotemporal feature extraction and data imbalance. Applied Sciences, 15(3), 1552. https://doi.org/10.3390/app15031552.
  26. [26] Sharma, B., Sharma, L., Lal, C., & Roy, S. (2023). Anomaly based network intrusion detection for IoT attacks using deep learning technique. Computers & Electrical Engineering, 107, 108626. https://doi.org/10.1016/j.compeleceng.2022.108626
  27. [27] Shu, X., Zhang, L., Qi, G. J., Liu, W., & Tang, J. (2022). Spatiotemporal co-attention recurrent neural networks for human-skeleton motion prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44, 3300–3315. https://doi.org/10.1109/TPAMI.2021.3099213
  28. [28] Raja, M. S. (2025). The rise of AI-driven network intrusion detection systems: Innovations, challenges, and future directions. International Journal of AI, Big Data, Computational and Management Studies, 6(1), 1–9. https://doi.org/10.63282/3050- 9416.IJAIBDCMS-V6I1P101
  29. [29] Ansam Khraisat, Ammar Alazab, Sarabjot Singh, Tony Jan, and Alfredo Jr. Gomez. 2024. Survey on Federated Learning for Intrusion Detection System: Concept, Architectures, Aggregation Strategies, Challenges, and Future Directions. ACM Comput. Surv. 57, 1, Article 7 (January 2025), 38 pages. https://doi.org/10.1145/3687124
  30. [30] Bui Duc Manh, Chi-Hieu Nguyen, Dinh Thai Hoang, Diep N. Nguyen.2024 Homomorphic Encryption-Enabled Federated Learning for Privacy-Preserving Intrusion Detection in Resource-Constrained IoV Networks https://doi.org/10.48550/arXiv.2407.18503
  31. [31] Manzoor, H. U., Shabbir, A., Chen, A., Flynn, D., & Zoha, A. (2024). A Survey of Security Strategies in Federated Learning: Defending Models, Data, and Privacy. Future Internet, 16(10), 374. https://doi.org/10.3390/fi16100374
  32. [32] Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016). Deep learning with differential privacy. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security https://doi.org/10.1145/2976749.2978318
  33. [33] Mikołajczyk-Bareła, A., Ferlin, M., & Grochowski, M. (2023, August 23). Targeted data augmentation for bias mitigation. Gdańsk University of Technology. https://doi.org/10.48550/arXiv.2308.11386
  34. [34] Gurung, K., Ghimire, A., & Amsaad, F. (26 July 2025). Enhancing IoT intrusion detection systems through adversarial training. Wright State University. https://doi.org/10.48550/arXiv.2507.19739
  35. [35] Marek Pawlicki, Aleksandra Pawlicka, Rafał Kozik, Michał Choraś, A metasurvey of adversarial attacks against artificial intelligence algorithms, including diffusion models, Neurocomputing, Volume 653, 2025,131231,ISSN 0925-2312, https://doi.org/10.1016/j.neucom.2025.131231.
  36. [36] Pastaltzidis, I., Dimitriou, N., Quezada-Tavárez, K., Aidinlis, S., Marquenie, T., Gurzawska, A., & Tzovaras, D. (2022-06-20). Data augmentation for fairness-aware machine learning: Preventing algorithmic bias in law enforcement systems. Centre for Research and Technology Hellas. https://doi.org/10.1145/3531146.3534644
  37. [37] Gaspar, D., Silva, P., & Silva, C. (2024). Explainable AI for intrusion detection systems: LIME and SHAP applicability on multi-layer perceptron. IEEE Access, 1–1. https://doi.org/10.1109/ACCESS.2024.3368377
  38. [38] Hermosilla, P., Berríos, S., & Allende-Cid, H. (2025). Explainable AI for Forensic Analysis: A Comparative Study of SHAP and LIME in Intrusion Detection Models. Applied Sciences, 15(13), 7329. https://doi.org/10.3390/app15137329
  39. [39] Mohale, V. Z., & Obagbuwa, I. C. (2025). A systematic review on the integration of explainable artificial intelligence in intrusion detection systems to enhancing transparency and interpretability in cybersecurity. Frontiers in artificial intelligence, 8, 1526221. https://doi.org/10.3389/frai.2025.1526221
  40. [40] M. T. Ribeiro, S. Singh and C. Guestrin, "Why should I trust you?"Explaining the predictions of any classifier, Proceedings of the 22ndACM SIGKDD international conference on knowledge discovery and datamining, 2016. https://doi.org/10.48550/arXiv.1602.04938
  41. [41] Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions [Preprint]. arXiv. https://doi.org/10.48550/arXiv.1705.07874
  42. [42] Kotecha, K., Dhupar, V., Chandra, S., & Kumar, M. (2022). Explainable artificial intelligence for intrusion detection system. Electronics, 11, 3079. https://doi.org/10.3390/electronics11193079
  43. [43] Huang, Y., Ul Hassan, W., Guo, Y., Chen, X., & Li, D. (2025, June 6). PROVSYN: Synthesizing provenance graphs for data augmentation in intrusion detection systems. arXiv preprint arXiv:2506.06226. https://arxiv.org/abs/2506.06226
  44. [44] Koukoulis, I., Syrigos, I., & Korakis, T. (2025, May 12). Self-supervised transformerbased contrastive learning for intrusion detection systems. Department of Electrical and Computer Engineering, University of Thessaly; Centre for Research and Technology Hellas (CERTH).https://doi.org/10.48550/arXiv.2505.08816
  45. [45] Mohammed, R., Rawashdeh, J., & Abdullah, M. (2020). Machine learning with oversampling and undersampling techniques: Overview study and experimental results. In 2020 International Conference on Information and Communication Technology for Intelligent Systems (ICICTIS) (pp. 243–248). IEEE. https://doi.org/10.1109/ICICS49469.2020.239556
  46. [46] Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTEq: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research, 16, 321–357. https://doi.org/10.1613/jair.953
  47. [47] Hasanin, T., & Khoshgoftaar, T. (2018). The effects of random undersampling with simulated class imbalance for big data. In 2018 IEEE International Conference on Information Reuse and Integration (IRI) (pp. 70–79). IEEE. https://doi.org/10.1109/IRI.2018.00018
  48. [48] Rapid7. (2024). 2024 attack intelligence report. https://www.rapid7.com/research/report/2024-attack-intelligence-report/
  49. [49] Cost of a Data Breach Report 2024. [Online]. Available: https://www.ibm.com/reports/data-breach
  50. [50] Gupta, R., Liu, S., Zhang, R., Hu, X., Wang, X., Benkraouda, H., Kommaraju, P., Cao, P., Feamster, N., & Nahrstedt, K. (n.d.). Generative active adaptation for drifting and imbalanced network intrusion detection. University of Illinois Urbana-Champaign and University of Chicago. https://doi.org/10.48550/arXiv.2503.03022
  51. [51] Chou, D., & Jiang, M. (2021). A survey on data-driven network intrusion detection. ACM Computing Surveys, 54(9), Article 182. https://doi.org/10.1145/3472753.
  52. [52] Guo, C., Li, X., Cheng, J., Yang, S., & Gong, H. (2025). Continual Learning for Intrusion Detection Under Evolving Network Threats. Future Internet, 17(10), 456. https://doi.org/10.3390/fi17100456
  53. [53] Zhang, X., Zhao, R., Jiang, Z., Chen, H., Ding, Y., Ngai, E. C. H., & Yang, S.- H. (2025). Continual learning with strategic selection and forgetting for network intrusion detection. The University of Hong Kong; Southern University of Science and Technology; University of Reading. https://arxiv.org/pdf/2412.16264?
  54. [54] Arreche, O., Abdallah, M. A comparative analysis of DNN-based white-box explainable AI methods in network security. EURASIP J. on Info. Security 2025, 16 (2025). https://doi.org/10.1186/s13635-025-00201-x
  55. [55] PapersFlow Research Team. (2026). Evaluation metrics for XAI methods: Research guide. PapersFlow. Evaluation metrics for XAI methods
  56. [56] Ogunseyi, T. B., Thiyagarajan, G., He, H., Bist, V., & Du, Z. (2026). Performance Analysis of Explainable Deep Learning-Based Intrusion Detection Systems for IoT Networks: A Systematic Review. Sensors, 26(2), 363. https://doi.org/10.3390/s26020363
  57. [57] . Anna L. Buczak, A. L., & Erhan Guven, E. (2016). A survey of data mining and machine learning methods for cyber security intrusion detection. IEEE Communications Surveys & Tutorials, 18(2), 1153–1176. https://doi.org/10.1109/COMST.2015.2494502
  58. [58] Ashwin, N. (2022). A survey: Deep learning based intrusion detection systems for IoT frameworks. International Journal of Scientific Research in Science and Technology, 9(3), 616–623
  59. [59] Nguyen Truong, K., Sun, K., Wang, S., Guitton, F., & Guo, Y. (2020). Privacy Preservation in Federated Learning: An insightful survey from the GDPR perspective. arXiv. https://arxiv.org/abs/2011.05411
  60. [60] Zhu, L., Liu, Z., & Han, S. (2019). Deep leakage from gradients. Advances in Neural Information Processing Systems, 32. https://doi.org/10.48550/arXiv.1906.08935
  61. [61] Acar, A., Aksu, H., Uluagac, A. S., & Conti, M. (2018). A survey on homomorphic encryption schemes: Theory and implementation. ACM Computing Surveys, 51. https://doi.org/10.48550/arXiv.1704.03578
  62. [62] Li, H., & Li, Z. (2025, July 9). Homomorphic encryption in federated learning: A systematic review of current methods and open challenges. SSRN. https://dx.doi.org/10.2139/ssrn.5358246
  63. [63] Tan, Q., Wu, S., & Tao, Y. (2023). Privacy-Enhanced Federated Learning for Non-IID Data. Mathematics, 11(19), 4123. https://doi.org/10.3390/math11194123
  64. [64] European Parliament & Council of the European Union. (2016). Regulation (EU) 2016/679 (General Data Protection Regulation). Official Journal of the European Union. https://gdpr-info.eu/
  65. [65] European Parliament & Council of the European Union. (2024). Regulation laying down harmonised rules on artificial intelligence (AI Act). Official Journal of the European Union. https://artificialintelligenceact.eu/the-act/
  66. [66] European Data Protection Board (2020). Guidelines 05/2020 on consent and automated decision-making. https://www.edpb.europa.eu
  67. [67] National Institute of Standards and Technology. (2023). Artificial Intelligence Risk Management Framework (AI RMF 1.0). https://nvlpubs.nist.gov/
  68. [68] National Assembly of the Republic of Korea. (2011, as amended). Personal Information Protection Act. https://elaw.klri.re.kr/
  69. [69] Personal Information Protection Commission. (2021, July 9). AI personal information protection self-checklist. https://www.pipc.go.kr
  70. [70] National Intelligence Service. (2024, November 29). Korea’s 2024 national cybersecurity white paper https://www.kisa.or.kr/EN/302/form?postSeq=73
  71. [71] Vijayan, J. (2021, November 30). 5 tips for reducing false positive security alerts. CSO Online. https://www.csoonline.com/article/571649/5-tips-for-reducing-false-positive-s ecurity-alerts.html