Mathematical modeling of explainable AI based false data injection attack detection for resilient artificial intelligence of things

Mohammed A. AlAqil; Hend Khalid Alkahtani; Nasser Allheeib; Jahangir Khan; Hanadi Alkhudhayr; Sami M. Alenezi; Malak Bakheet Alharbi; Sultan Almutairi; Mohammed A. AlAqil; Hend Khalid Alkahtani; Nasser Allheeib; Jahangir Khan; Hanadi Alkhudhayr; Sami M. Alenezi; Malak Bakheet Alharbi; Sultan Almutairi

doi:10.3934/math.2026583

AIMS Mathematics

2026, Volume 11, Issue 5: 14211-14238. doi: 10.3934/math.2026583

Previous Article Next Article

Research article Special Issues

Mathematical modeling of explainable AI based false data injection attack detection for resilient artificial intelligence of things

1.
Department of Electrical Engineering, College of Engineering, King Faisal University, Al Ahsa, Saudi Arabia
2.
Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia
3.
Department of Information Systems, College of Computer and Information Sciences, King Saud University, Riyadh 11495, Saudi Arabia
4.
Department of Computer Science, Applied College at Mahayil, King Khalid University, Saudi Arabia
5.
Department of Information Systems, Faculty of Computing and Information Technology, King Abdulaziz University, Rabigh 25732, Saudi Arabia
6.
Department of Computer Science, College of Science, Northern Border University, Arar, 91431, Saudi Arabia
7.
Department of Software Engineering, College of Computer Science and Engineering, University of Jeddah, Saudi Arabia
8.
Department of Computer Science, Applied College, Shaqra University, Shaqra 15526, Saudi Arabia

Received: 14 February 2026 Revised: 28 March 2026 Accepted: 08 April 2026 Published: 19 May 2026
MSC : 68T07, 68T45

The artificial intelligence of things (AIoT) comprises the integration of artificial intelligence (AI) technologies and the internet of things (IoT) infrastructure. The main aim of the AIoT is to design highly effective IoT operation, enhance human-machine interaction, and improve data analytics and data management. In the AIoT system, the AI is embedded into the infrastructure elements, namely programs and chipsets, which are interlinked via the IoT network. Cybersecurity in the AIoT employs AI technologies, particularly machine learning (ML), deep learning (DL), and neural networks to defend connected IoT devices, networks, and data from recent cyber threats. Since IoT devices have restricted capability, storage, and power, the AI offers intelligent and effective defenses that can learn to identify anomalies in real time. Therefore, we present a mathematically guided and explainable AI-based framework titled the mutual information-based feature ranking for detecting false data injection attacks (MIFR-DFDIA) approach in resilient distributed cybersecurity networks. The MIFR-DFDIA aims to enhance cybersecurity resilience by accurately identifying and mitigating false data injection attacks that compromise data integrity. Initially, data preprocessing was performed to handle outliers, missing values, and feature standardization for ensuring high-quality input data for analysis. Mutual information was then utilized for optimal feature selection to identify the most informative attributes effectively. For classification, a hybrid model such as a stacked variational autoencoder and a wasserstein generative adversarial network was deployed for robust and precise recognition of false data injection attacks in cybersecurity distributed systems. Finally, the explainable artificial intelligence (XAI) method based SHAP was incorporated to interpret model predictions and improve transparency in decision-making. The experimental result analysis of the MIFR-DFDIA method was carried out for a benchmark dataset, and the comparative analysis exhibited the improved solution over other techniques concerning various metrics.
- artificial intelligence of things,
- false data injection attacks,
- cybersecurity,
- explainable artificial intelligence,
- distributed security
Citation: Mohammed A. AlAqil, Hend Khalid Alkahtani, Nasser Allheeib, Jahangir Khan, Hanadi Alkhudhayr, Sami M. Alenezi, Malak Bakheet Alharbi, Sultan Almutairi. Mathematical modeling of explainable AI based false data injection attack detection for resilient artificial intelligence of things[J]. AIMS Mathematics, 2026, 11(5): 14211-14238. doi: 10.3934/math.2026583

Related Papers:

Abstract

The artificial intelligence of things (AIoT) comprises the integration of artificial intelligence (AI) technologies and the internet of things (IoT) infrastructure. The main aim of the AIoT is to design highly effective IoT operation, enhance human-machine interaction, and improve data analytics and data management. In the AIoT system, the AI is embedded into the infrastructure elements, namely programs and chipsets, which are interlinked via the IoT network. Cybersecurity in the AIoT employs AI technologies, particularly machine learning (ML), deep learning (DL), and neural networks to defend connected IoT devices, networks, and data from recent cyber threats. Since IoT devices have restricted capability, storage, and power, the AI offers intelligent and effective defenses that can learn to identify anomalies in real time. Therefore, we present a mathematically guided and explainable AI-based framework titled the mutual information-based feature ranking for detecting false data injection attacks (MIFR-DFDIA) approach in resilient distributed cybersecurity networks. The MIFR-DFDIA aims to enhance cybersecurity resilience by accurately identifying and mitigating false data injection attacks that compromise data integrity. Initially, data preprocessing was performed to handle outliers, missing values, and feature standardization for ensuring high-quality input data for analysis. Mutual information was then utilized for optimal feature selection to identify the most informative attributes effectively. For classification, a hybrid model such as a stacked variational autoencoder and a wasserstein generative adversarial network was deployed for robust and precise recognition of false data injection attacks in cybersecurity distributed systems. Finally, the explainable artificial intelligence (XAI) method based SHAP was incorporated to interpret model predictions and improve transparency in decision-making. The experimental result analysis of the MIFR-DFDIA method was carried out for a benchmark dataset, and the comparative analysis exhibited the improved solution over other techniques concerning various metrics.

References

[1]	F. Charmet, H. C. Tanuwidjaja, S. Ayoubi, P. F. Gimenez, Y. F. Han, H. Jmila, et al., Explainable artificial intelligence for cybersecurity: a literature survey, Ann. Telecomm., 77 (2022), 789–812. https://doi.org/10.1007/s12243-022-00926-7 doi: 10.1007/s12243-022-00926-7
[2]	A. Shees, M. Tariq, A. I. Sarwat, Cybersecurity in smart grids: detecting false data injection attacks utilizing supervised machine learning techniques, Energies, 17 (2024), 5870. https://doi.org/10.3390/en17235870 doi: 10.3390/en17235870
[3]	F. Almutairy, L. Scekic, R. Elmoudi, S. Wshah, Accurate detection of false data injection attacks in renewable power systems using deep learning, IEEE Access, 9 (2021), 135774–135789. https://doi.org/10.1109/ACCESS.2021.3117230 doi: 10.1109/ACCESS.2021.3117230
[4]	A. Sayghe, Y. D. Hu, I. Zografopoulos, X. R. Liu, R. G. Dutta, Y. Jin, et al., Survey of machine learning methods for detecting false data injection attacks in power systems, IET Smart Grid, 3 (2020), 581–595. https://doi.org/10.1049/iet-stg.2020.0015 doi: 10.1049/iet-stg.2020.0015
[5]	Y. Zhang, J. H. Wang, B. Chen, Detecting false data injection attacks in smart grids: a semi-supervised deep learning approach, IEEE Trans. Smart Grid, 12 (2021), 623–634. https://doi.org/10.1109/TSG.2020.3010510 doi: 10.1109/TSG.2020.3010510
[6]	Y. C. Ding, K. Ma, T. J. Pu, X. Y. Wang, R. Li, D. X. Zhang, A deep learning-based classification scheme for false data injection attack detection in the power system, Electronics, 10 (2021), 1459. https://doi.org/10.3390/electronics10121459 doi: 10.3390/electronics10121459
[7]	X. Y. Niu, J. N. Li, J. Y. Sun, K. Tomsovic, Dynamic detection of false data injection attack in smart grid using deep learning. In: 2019 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), 2019, 1–6. https://doi.org/10.1109/ISGT.2019.8791598
[8]	G. R. Mode, P. Calyam, K. A. Hoque, Impact of false data injection attacks on deep learning enabled predictive analytics, In: NOMS 2020-2020 IEEE/IFIP Network Operations and Management Symposium, Budapest, Hungary, 2020, 1–7. https://doi.org/10.1109/NOMS47738.2020.9110395
[9]	M. Elnour, M. Noorizadeh, M. Shakerpour, N. Meskin, K. Khan, R. Jain, A machine learning based framework for real-time detection and mitigation of sensor false data injection cyber-physical attacks in industrial control systems, IEEE Access, 11 (2023), 86977–86998. https://doi.org/10.1109/ACCESS.2023.3303015 doi: 10.1109/ACCESS.2023.3303015
[10]	D. Mukherjee, S. Chakraborty, A. Y. Abdelaziz, A. El-Shahat, Deep learning-based identification of false data injection attacks on modern smart grids, Energy Reports, 8 (2022), 919–930. https://doi.org/10.1016/j.egyr.2022.10.270 doi: 10.1016/j.egyr.2022.10.270
[11]	H. Moayyed, M. Mohammadpourfard, C. Konstantinou, A. Moradzadeh, B. Mohammadi-Ivatloo, A. P. Aguiar, Image processing based approach for false data injection attacks detection in power systems, IEEE Access, 10 (2022), 12412–12420. https://doi.org/10.1109/ACCESS.2021.3131506 doi: 10.1109/ACCESS.2021.3131506
[12]	D. B. Unsal, T. S. Ustun, S. M. S. Hussain, A. Onen, Enhancing cybersecurity in smart grids: false data injection and its mitigation, Energies, 14 (2021), 2657. https://doi.org/10.3390/en14092657 doi: 10.3390/en14092657
[13]	A. Sargolzaei, K. Yazdani, A. Abbaspour, C. D. Crane III, W. E. Dixon, Detection and mitigation of false data injection attacks in networked control systems, IEEE Trans. Ind. Inform., 16 (2020), 4281–4292. https://doi.org/10.1109/TII.2019.2952067 doi: 10.1109/TII.2019.2952067
[14]	V. Soni, D. Mehta, A. Shah, S. Dhingani, R. Gupta, S. Tanwar, et al., Explainable machine leaning-based false data injection classification framework for Avs, In: 2025 IEEE International Conference on Communications Workshops (ICC Workshops), Montreal, QC, Canada, 2025, 1924–1929. https://doi.org/10.1109/ICCWorkshops67674.2025.11162467
[15]	P. Jain, A. Rathour, A. Sharma, G. S. Chhabra, Bridging explainability and security: an XAI-enhanced hybrid deep learning framework for IoT device identification and attack detection, IEEE Access, 13 (2025), 127368–127390. https://doi.org/10.1109/ACCESS.2025.3590159 doi: 10.1109/ACCESS.2025.3590159
[16]	J. P. Ji, Y. Liu, J. Chen, Z. W. Yao, M. D. Zhang, Y. Y. Gong, False data injection attack detection method based on deep learning with multi-scale feature fusion, IEEE Access, 12 (2024), 89262–89274. https://doi.org/10.1109/ACCESS.2024.3418883 doi: 10.1109/ACCESS.2024.3418883
[17]	H. T. Feng, Y. H. Han, K. K. Li, F. Y. Si, Q. Zhao, Locational detection of the false data injection attacks via semi-supervised multi-label adversarial network, Int. J. Electr. Power Energy Syst., 155 (2024), 109682. https://doi.org/10.1016/j.ijepes.2023.109682 doi: 10.1016/j.ijepes.2023.109682
[18]	H. Alamro, K. Mahmood, S. S. Aljameel, A. Yafoz, R. Alsini, A. Mohamed, Modified red fox optimizer with deep learning enabled false data injection attack detection, IEEE Access, 11 (2023), 79256–79264. https://doi.org/10.1109/ACCESS.2023.3298056 doi: 10.1109/ACCESS.2023.3298056
[19]	R. Huang, Y. C. Li, X. Wang, Attention-aware deep reinforcement learning for detecting false data injection attacks in smart grids, Int. J. Electr. Power Energy Syst., 147 (2023), 108815. https://doi.org/10.1016/j.ijepes.2022.108815 doi: 10.1016/j.ijepes.2022.108815
[20]	E. Naderi, A. Asrari, A deep learning framework to identify remedial action schemes against false data injection cyberattacks targeting smart power systems, IEEE Trans. Ind. Inform., 20 (2024), 1208–1219. https://doi.org/10.1109/TII.2023.3272625 doi: 10.1109/TII.2023.3272625
[21]	H. B. Guo, J. Sun, Z. H. Pang, Residual-based false data injection attacks against multi-sensor estimation systems, IEEE/CAA J. Automat. Sinica, 10 (2023), 1181–1191. https://doi.org/10.1109/JAS.2023.123441 doi: 10.1109/JAS.2023.123441
[22]	H. Zhou, D. C. Ren, H. X. Xia, M. Y. Fan, X. Yang, H. Huang, AST-GNN: An attention-based spatio-temporal graph neural network for interaction-aware pedestrian trajectory prediction, Neurocomputing, 445 (2021), 298–308. https://doi.org/10.1016/j.neucom.2021.03.024 doi: 10.1016/j.neucom.2021.03.024
[23]	M. Y. Fan, X. Q. Zhang, J. Hu, N. N. Gu, D. C. Tao, Adaptive data structure regularized multiclass discriminative feature selection, IEEE Trans. Neural Networks Learn. Syst., 33 (2022), 5859–5872. https://doi.org/10.1109/TNNLS.2021.3071603 doi: 10.1109/TNNLS.2021.3071603
[24]	L. Q. Yang, Y. Zhai, Z. J. Li, Deep learning for online AC false data injection attack detection in smart grids: an approach using LSTM-autoencoder, J. Network Comput. Appl., 193 (2021), 103178. https://doi.org/10.1016/j.jnca.2021.103178 doi: 10.1016/j.jnca.2021.103178
[25]	J. W. Tian, C. Shen, C. H. Lin, M. Zhang, X. F. Xia, C. Ren, ADMM-based adversarial false data injection attacks against multi-label locational detection, IEEE Trans. Depend. Secure Comput., 23 (2026), 263–277. https://doi.org/10.1109/TDSC.2025.3605689 doi: 10.1109/TDSC.2025.3605689
[26]	J. W. Tian, C. Shen, B. H. Wang, X. F. Xia, M. Zhang, C. H. Lin, LESSON: Multi-label adversarial false data injection attack for deep learning locational detection, IEEE Trans. Depend. Secure Comput., 21 (2024), 4418–4432. https://doi.org/10.1109/TDSC.2024.3353302 doi: 10.1109/TDSC.2024.3353302
[27]	M. T. Nguyễn, T. L. Nhat, Identifying risk factors and survival prediction of heart failure patients using machine learning, J. Sci. Technol. Inform. Commun., 1 (2025), 3–10.
[28]	C. Y. Liu, X. M. Yu, P. L. Wu, H. Y. Wang, A novel 3D indoor localization method integrating deep spatial feature augmentation and attention-based denoising, Sci. Rep., 15 (2025), 33025. https://doi.org/10.1038/s41598-025-18549-y doi: 10.1038/s41598-025-18549-y
[29]	P. N. Srinivasu, M. Sailaja, S. C. Narahari, P. Barsocchi, A. K. Bhoi, XAI driven software defect prediction using adaptive feature engineering coupled with autoencoder and multi-layer perceptron: an empirical study, IEEE Access, 13 (2025), 168693–168710. https://doi.org/10.1109/ACCESS.2025.3603451 doi: 10.1109/ACCESS.2025.3603451
[30]	False data injection attack dataset for industrial internet of things, 2025. Available from: https://zenodo.org/records/14864902.
[31]	Industrial IoT dataset (Synthetic). Available from: https://www.kaggle.com/datasets/canozensoy/industrial-iot-dataset-synthetic/data?select = factory_sensor_simulator_2040.csv.
[32]	H. Wang, J. Y. Yang, J. Sun, Z. Wang, Q. Z. Liu, S. X. Luo, FedIFD: Identifying false data injection attacks in internet of vehicles based on federated learning, Big Data Cogn. Comput., 9 (2025), 246. https://doi.org/10.3390/bdcc9100246 doi: 10.3390/bdcc9100246
[33]	T. Li, T. Xia, H. M. Zhang, D. Y. Liu, H. Zhao, Z. L. Liu, False data injection attacks detection based on stacking and MIC-DCXGB, Sustainability, 16 (2024), 9692. https://doi.org/10.3390/su16229692 doi: 10.3390/su16229692
[34]	A. Gueriani, H. Kheddar, A. C. Mazari, M. C. Ghanem, A robust cross-domain IDS using BiGRU-LSTM-attention for medical and industrial IoT security, ICT Express, 2025, In press. https://doi.org/10.1016/j.icte.2025.08.011
[35]	M. N. A. Ramadan, M. A. H. Ali, H. Jaber, M. Alkhedher, Blockchain-secured IoT-federated learning for industrial air pollution monitoring: a mechanistic approach to exposure prediction and environmental safety, Ecotox. Environ. Safety, 300 (2025), 118442. https://doi.org/10.1016/j.ecoenv.2025.118442 doi: 10.1016/j.ecoenv.2025.118442

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)