Volume 5 , Issue 2 , PP: 13–21, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Rozina Ali 1 *
Doi: https://doi.org/10.54216/NIF.050202
Real-time Internet of Things intrusion attribution is often formulated as direct multi-class classification, although packet traces contain incomplete, conflicting, and imbalanced evidence. This paper develops a mathematical neutrosophic signature calculus in which each flow is represented by truth, indeterminacy, and falsity memberships over class-specific attack signatures. The proposed model constructs entropy-contrast behavioral channels, maps each flow to class prototypes through a contradiction-aware single-valued neutrosophic transformation, and derives a closed-form attribution rule by coupling prototype truth, opposite-region falsity pressure, and explicit indeterminacy penalization. The study uses RT-IoT2022, a public UCI benchmark donated in 2024 with 123,117 flows, 83 features, and 12 normal/attack labels. The results show that the proposed calculus provides interpretable class attribution and stable macro-level behavior under severe class imbalance. The work supports neutrosophic signature modeling as a transparent route for IoT security decision support under inconsistent network evidence.
Single-valued neutrosophic set , Intrusion attribution , IoT security , Contradiction score , Uncertainty-aware classification , Information fusion
[1] Almohaimeed, M. (2024). Enhancing IoT network security using feature selection for intrusion detection systems. Applied Sciences, 14(24), 11966. https://doi.org/10.3390/app142411966
[2] Alsharari, F., Alohali, H., Saber, Y., & Smarandache, F. (2024). An introduction to single-valued neutrosophic primal theory. Symmetry, 16(4), 402. https://doi.org/10.3390/sym16040402
[3] Farid, H. M. A. (2023). Single-valued neutrosophic dynamic aggregation information with time sequence preference for IoT technology in supply chain management. Engineering Applications of Artificial Intelli-gence, 126, 106940. https://doi.org/10.1016/j.engappai.2023.106940
[4] Kamaci, H. (2021). Linguistic single-valued neutrosophic soft sets with applications in game theory. Interna-tional Journal of Intelligent Systems, 36, 3917–3960. https://doi.org/10.1002/int.22445
[5] Kamran, M., Ashraf, S., Salamat, N., Naeem, M., & Botmart, T. (2023). Cyber security control selection based decision support algorithm under single valued neutrosophic hesitant fuzzy Einstein aggregation information. AIMS Mathematics, 8(3), 5551–5573. https://doi.org/10.3934/math.2023280
[6] Nguyen, P. H. (2024). Assessing cybersecurity risks and prioritizing top strategies in Vietnam’s finance and banking system using strategic decision-making models-based neutrosophic sets and Z number. Heliyon. https://doi.org/10.1016/j.heliyon.2024.e39842
[7] Sharmila, B. S., & Nagapadma, R. (2023). Quantized autoencoder (QAE) intrusion detection system for anomaly detection in resource-constrained IoT devices using RT-IoT2022 dataset. Cybersecurity, 6(1), 41. https://doi.org/10.1186/s42400-023-00178-5
[8] Sharmila, B. S., & Nagapadma, R. (2024). RT-IoT2022 [Data set]. UCI Machine Learning Repository. https://doi.org/10.24432/C5P338
[9] Tan, R. P., & Zhang, W. D. (2021). Decision-making method based on new entropy and refined singlevalued neutrosophic sets and its application in typhoon disaster assessment. Applied Intelligence, 51, 283– 307. https://doi.org/10.1007/s10489-020-01706-3
