Explainable Intrusion Detection for Cyber Defences in the Internet of Things: Opportunities and Solutions
The DOI matches its Crossref record; 191 of the 192 references it cites were found in a registry or an index, and 1 are not checked yet.
Abstract
The field of Explainable Artificial Intelligence (XAI) has garnered considerable research attention in recent years, aiming to provide interpretability and confidence to the inner workings of state-of-the-art deep learning models. However, XAI-enhanced cybersecurity measures in the Internet of Things (IoT) and its sub-domains, require further investigation to provide effective discovery of attack surfaces, their corresponding vectors, and interpretable justification of model outputs. Cyber defence involves operations conducted in the cybersecurity field supporting mission objectives to identify and prevent cyberattacks using various tools and techniques, including intrusion detection systems (IDS), threat intelligence and hunting, and intrusion prevention. In cyber defence, especially anomaly-based IDS, the emerging applications of deep learning models require the interpretation of the models’ architecture and the explanation of models’ prediction to examine how cyberattacks would occur. This paper presents a comprehensive review of XAI techniques for anomaly-based intrusion detection in IoT networks. Firstly, we review IDSs focusing on anomaly-based detection techniques in IoT and how XAI models can augment them to provide trust and confidence in their detections. Secondly, we review AI models, including machine learning (ML) and deep learning (DL), for anomaly detection applications and IoT ecosystems. Moreover, we discuss DL’s ability to effectively learn from large-scale IoT datasets, accomplishing high performances in discovering and interpreting security events. Thirdly, we demonstrate recent research on the intersection of XAI, anomaly-based IDS and IoT. Finally, we discuss the current challenges and solutions of XAI for security applications in the cyber defence perspective of IoT networks, revealing future research directions. By analysing our findings, new cybersecurity applications that require XAI models emerge, assisting decision-makers in understanding and explaining security events in compromised IoT networks.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“By integrating XAI techniques, these models can highlight which features such as unusual packet sizes, protocol usage, or temporal patterns triggered an anomaly flag, thereby aiding analysts in decision-making and improving system resilience (Moustafa et al., 2023).”
From Explainable AI: enhancing decision-making in the detection of cyber threats (2026) · cites this paper as Moustafa et al., 2023
In the citing paper
“In cybersecurity practice, XAI has become critical not only for intrusion detection systems, where it helps reduce false positives and improve analyst trust, but also in IoT and IIoT networks, where it highlights abnormal device behavior, and in forensic and compliance contexts, where transparency is necessary to meet regulatory demands such as the EU AI Act (Nwakanma et al., 2023;Moustafa et al.,”
From Explainable AI: enhancing decision-making in the detection of cyber threats (2026) · cites this paper as Moustafa et al., 2023
In the citing paper
“Likewise, Moustafa et al. (2023) stress that this problem is particularly acute in IoTfocused domains, where inconsistent assessment undermines confidence in proposed solutions.”
From Explainable AI: enhancing decision-making in the detection of cyber threats (2026) · cites this paper as Moustafa et al. (2023)
In the citing paper
“Moustafa et al. (2023) explicitly highlight that “most current XAI methods produce results that only make sense to researchers, ” emphasizing that while the academic community may appreciate the novelty of these methods, they remain inaccessible to those working on the frontlines of cybersecurity defence.”
From Explainable AI: enhancing decision-making in the detection of cyber threats (2026) · cites this paper as Moustafa et al. (2023)
In the citing paper
“While partial dependence plots result in a significantly biased computed feature effect, ALEs provide a faster and unbiased substitute for visualisation [138,139].”
From Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence (2024) · cites this paper as [138]
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 2×
“The Permutation Feature Importance (PFI) was first introduced in 2001 by Breiman [144] and measures the increase in prediction error of a fitted model after permuting the feature’s values.”
BackgroundA Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
Gauriat, C.-M., Pencolé, Y., Ribot, P., & Brouillet, G. (2024) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.4230/oasics.dx.2024.27 · Cited by 12,586
Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1910.10045 · Cited by 11,321
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423
17. A Value for n-Person Games
Shapley, L. S. (1953) · Contributions to the Theory of Games (AM-28), Volume II · doi:10.1515/9781400881970-018 · Cited by 6,950
“Why Should I Trust You?”: Explaining the Predictions of Any Classifier
Ribeiro, M., Singh, S., & Guestrin, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations · doi:10.18653/v1/n16-3020 · Cited by 6,682
A Comprehensive Survey on Transfer Learning
Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H., & He, Q. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2020.3004555 · Cited by 6,678 · cited 2×
“Semi-supervised learning is helpful in many scenarios when data collecting is expensive, time-consuming or even unrealistic [112].”
BackgroundMethodPeeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Adadi, A., & Berrada, M. (2018) · IEEE Access · doi:10.1109/access.2018.2870052 · Cited by 6,294
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370
Research works printed but not linked: 28
- Morgan, 2020, Cybercrime to Cost the World $10.5 Trillion Annually by 2025
- 2021, Australian cyber security centre annual cyber threat report 2020–21
- Das, 2018, Direct costs associated with cybersecurity incidents costs Australian businesses $29 billion per annum
- 2020, U.S. government to spend over $18 billion on cybersecurity—Atlas VPN
- De Luca, 2021, Explainable artificial intelligence for workflow verification in visual IoT/robotics programming language environment, J. Artif. Intell. Technol., 1, 21
- 2021, Explainable and trustworthy artifcial intelligence
- 2021, Explainable AI for healthcare
- 2021, Theoretic foundation, criticism, and application trend of explainable AI
- 2020, Explainable artificial intelligence
- 2020, Interpretable & explainable machine vision
- 2019, Interpreting, explaining and visualizing deep learning
- 2019, Explainable deep learning for efficient and robust pattern recognition
- 2019, Explainable artificial intelligence (XAI)
- 2019, Interpretating and explaining visual artifcial intelligence models
- 2020, Explainable artificial intelligence (XAI)
- 2020, ACM conference on fairness, accountability, and transparency
- 2019, What happens when self-driving cars kill people
- Martin, 2021, Cyber kill chain
- Singh, 2014, Computer network and information security, Comput. Netw. Inf. Security, 8, 41
- Anderson, Evading machine learning malware detection, 9
- Goodfellow, 2016, Deep Learning, 1
- Raschka, 2017, Python Machine Learning—Second Edition
- 10.5555/3045118.3045336 · doi:10.5555/3045118.3045336
- 10.2307/2699986 · doi:10.2307/2699986
- 2016, Fog Computing and the Internet of Things: Extend the Cloud to Where the Things Are
- 2020, 2020 unit 42 IoT threat report
- Amershi, 2020, Research collection: Research supporting Responsible Ai
- 2021, Responsible AI practices
Cited by
Items 201–300 of 325
Cecchi, G., Benelli, F., Caronna, M., Palma, G., & Rizzo, A. (2026) · Journal of Cybersecurity and Privacy · doi:10.3390/jcp6030091 · Cited by 3
Hossan, M. I., Rubel, M. S. K. C., Rahman, M. A., & Haque, B. M. T. (2025) · Journal of Ai ML DL · doi:10.25163/ai.1110763 · Cited by 1
“This is not merely a research nicety — it is a practical prerequisite for deployment in regulated critical infrastructure environments where accountability requirements apply (Moustafa et al., 2023; Fard et al., 2023).”
InfluentialDriss, M., Atitallah, S. B., Ammar, A., & Boulila, W. (2026) · Internet of Things · doi:10.1016/j.iot.2026.102010 · Cited by 1
Caldeira, I. D. B., Noya, R. C., & Salles, R. M. (2026) · IEEE Access · doi:10.1109/access.2026.3709613 · Cited by 1
“Despite the recent literature regarding XAI applications in cybersecurity [11], research concerning its efficacy across different network planes and the integrity of explanations within sovereign infrastructures remains fragmented.”
TRACE: Feature-Space Feasible Action Contracts for Explainable Intrusion Triage
Le, T. D., Arifuzzaman, M., & Bao, Y. (2026) · Electronics · doi:10.3390/electronics15153291 · Cited by 1
UĞURLU, M., & Doğru, İ. A. (2026) · Applied Sciences · doi:10.3390/app16167919 · Cited by 1
Farsimadan, E., Moradi, L., & Palmieri, F. (2026) · Internet of Things · doi:10.1016/j.iot.2026.102078 · Cited by 1
Fu, X., Li, J., Zhong, H., Wang, D., Chen, W., & Li, F. (2026) · Computer Science Review · doi:10.1016/j.cosrev.2026.101049 · Cited by 1
Hnamte, V. (2026) · Measurement Digitalization · doi:10.1016/j.meadig.2026.100060 · Cited by 1
Application of Trustworthy IoT Technology in Fast Communities: Smart Access Control
Yasmin, F., Ali, M. S. M., & Sultana, S. (2024) · European Journal of Theoretical and Applied Sciences · doi:10.59324/ejtas.2024.2(3).06 · Cited by 1
Liu, L., Ahmad, R., Ahmad, S., & Jiang, X. (2024) · Journal of Autonomous Intelligence · doi:10.32629/jai.v7i5.1577 · Cited by 1
Navigating Cryptocurrency Regulation: Trailblazing Legal Strategies for a Borderless Future
Singh, B., & Kaunert, C. (2024) · Advances in hospitality, tourism and the services industry (AHTSI) book series · doi:10.4018/979-8-3693-6562-5.ch009 · Cited by 1
Editorial: Third Quarter 2023 IEEE Communications Surveys and Tutorials
Niyato, D. T. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3301328 · Cited by 1
Machine Learning for Industrial Iot Cybersecurity: A Systematic ReviewPreprint
Dohin, A., Zkik, K., Akilal, A., Omar, M., & Akli, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5388573 · Cited by 2
Tolay, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.10349 · Cited by 1
“These dependencies are especially consequential in IoT networks, where heterogeneous devices and constrained monitoring points create different traffic and resource conditions from conventional enterprise networks [1, 2].”
Explainable Anomaly Detection for System Logs in Distributed Environments
Gu, Z., Yue, W., & Liu, C. (2026) · Computers, Materials & Continua · doi:10.32604/cmc.2026.077388
“Existing federated explainable methods often suffer from misalignment or invalidation of explanations because they fail to adapt to these characteristics [15].”
Mohamed, A. S., Fritz, C., Saber, A. M., Ma, Y., Kaur, R., Al-Darwbi, M., Friedrich, D., & Kundur, D. (2026) · arXiv · doi:10.48550/arxiv.2609.00171
“▲ Limited ✗ None [18] Reviews XAI for IDS in IoT environments.”
Towards Anomaly Traffic Detection with Causal Interpretability Methods
Zeng, Z., Zhao, B., Liu, X., & Deng, X. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-3890-8_7
Ding, Y., Xu, S., Peng, X., Yang, C., Liang, H., & Li, Z. (2024) · Research Square · doi:10.21203/rs.3.rs-4721338/v1
Singh, B., & Kaunert, C. (2024) · Advances in digital crime, forensics, and cyber terrorism book series · doi:10.4018/979-8-3693-8944-7.ch012
Singh, B., & Kaunert, C. (2024) · Advances in human and social aspects of technology book series · doi:10.4018/979-8-3693-9235-5.ch008 · Cited by 3
Enhanced Web Security Using Cross-Feature Analysis of Visual Design, Live Logs and Code Structures
Kumar, R., Sharma, T., & Saranya, G. (2024) · International Conference on Communication and Electronics Systems (ICCES) · doi:10.1109/icces63552.2024.10859763
“[5] Phishing detection and intrusion detection for cyber-physical systems (CPS) reveals significant advancements in cybersecurity, especially in the realm of machine learning (ML) and explainable AI (XAI).”
Anomaly classification in IIoT edge devices
de Antioquia, U., Múnera, D., Tobón, D. P., de Antioquia, U., Rodríguez, M., & de Antioquia, U. (2025) · Revista Facultad de Ingeniería Universidad de Antioquia · doi:10.17533/udea.redin.20250368
A Threat Flow Classification Method Based on Feature Fusion and Weighted Attention
Tu, Y., Wu, Y. C., Feng, S., Ren, J., Shen, H., Zhang, Y., & Liu, Q. (2025) · International Journal of Communication Systems · doi:10.1002/dac.70092
Network Intrusion Detection Systems An Evaluation of Black-Box Explainable AI Frameworks (E-XAI)
Umasankar, S., Viswanath, G., Bharathi, V. M., & Prathyusha, G. (2025) · International Journal of Applied Engineering and Management Letters · doi:10.47992/ijaeml.2581.7000.0235
Enhancing Intrusion Detection in CPS and IIoT with Lightweight Explainable AI Models
Ericson, A., Thar, K., & Forsström, S. (2025) · IEEE International Workshop on Factory Communication Systems (WFCS) · doi:10.1109/wfcs63373.2025.11077567 · Cited by 1
“CPS and IIoT networks are often characterized by distributed architectures, heterogeneous devices, and real-time operational constraints, making them vulnerable to a wide range of cyber threats [10], [11].”
Privacy-Preserving Sketch-Based Big Data Traffic Detection
Zhang, C., Liu, Y., Ren, X., Xu, J., Wang, Y., & Zhu, L. (2025) · International Conference on Big Data and Privacy Computing (BDPC) · doi:10.1109/bdpc63545.2025.11135568
“Accurate and timely traffic detection plays a pivotal role in this process, as it enables the identification of abnormal patterns that could indicate potential threats, such as Distributed Denial of Service (DDoS) attacks or data exfiltration attempts [2].”
Artificial Intelligence and the Internet of Things
Samaraweera, C., Bhattarai, A., Peng, D., Liu, Y., & Sharif, H. (2025) · Wiley eBooks · doi:10.1002/9781394280490.ch7
A Comprehensive Survey of Moving Target Defense: Perspectives and Applications in Malware MitigationPreprint
William, T., & ElkanaEbinazer, S. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5579871
Design of Enterprise Data Security Management Based on IoT and CNN
Gao, F. (2025) · Annals of Emerging Technologies in Computing · doi:10.33166/aetic.2025.04.005
A literature review on sinkhole attack detection for Internet of Things
Nadim, M., Eugenio, J. R., & Chennamaneni, A. (2025) · Ad Hoc Networks · doi:10.1016/j.adhoc.2025.104081 · Cited by 3
Bu, K., & Yao, W. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3643936
“Smaller IoT, wearables, and sensors are susceptible to fraudulent attacks, lowered performance, and unauthorized access, and it could compromise user privacy, data security, and functionality of devices [6].”
Attention-Based Deep Learning for Scenario Description Embedding in Cyber Threat Records
Benlalia, Z., Mzili, T., Hankar, M., Abatal, A., Mzili, M., Bačanin, N., & Shaheen, M. (2025) · Shifra. · doi:10.70470/shifra/2025/013
“[13 ] Another critical vulnerability detailed is the lack of monitoring of the 'wevtutil' utility, which is often trusted but rarely scrutinized.”
Li, J. T. M., & Yau, P. C. (2025) · International Conference on Computer Systems (ICCS) · doi:10.1109/iccs67844.2025.11291869
Optimizing Network-Level Forensics with Optuna-Generated CNN Model
Wilson, L. W. S., Kiat, J. Y. J., Buddy, N. Z. H., Mei, K. G. S., Alvin, A. P. C., & Mohan, P. (2024) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon61640.2024.10902935
“These mechanisms may include analyzing patterns, frequency of interactions, the speed and timing of actions, and the consistency of usage patterns [7].”
Sovrano, F., Vilone, G., Lognoul, M., & Longo, L. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5371124 · Cited by 5
Improving Network and IoT Intrusion Detection Through Machine Learning Algorithms
Sriramulu Deenadayala Babu, P. (2024) · TRAP@NCI (National College of Ireland)
Silva, H. O. (2025) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) · Cited by 4
Machine Learning-Based Intrusion Detection System for Enhancing Network Security for IoT Environment
Kulshreshtha, V., Jain, P., & Sharma, H. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5370-6_36
Hoang, H. D., Hien, D. T. T., Cam, N. T., & Pham, V.-H. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-02362-9_21
Explainable Machine Learning Model for Android Malware Detection
Divish Raj, O., & Hegde, D. V. V. (2025) · International Journal of Emerging Science and Engineering · doi:10.35940/ijese.l2617.13111025
Research on Communication Signal Recognition based on CNN-LSTM Neural Networks
Wen, Z., Wang, Y., Li, G., & Zhang, Y. (2025) · International Conference on Aerospace Information Perception and Intelligent Processing (AIPIP) · doi:10.1109/aipip66876.2025.11299206
“In this study, an improved CNN-LSTM neural network model is proposed [7[8][9] .”
Detecting Stealthy Anomalies with Autoencoders Using Windowed Variance-Aware Loss Functions
Hwang, L., Islam, M. N., Ali, M. H., Dasgupta, D., & Won, M. (2025) · IEEE Military Communications Conference (MILCOM) · doi:10.1109/milcom64451.2025.11310014
“Recently, transformer based architectures and autoencoders are proven to have a more advanced unsupervised anomaly detection capabilities, especially in the domain of Internet of Things (IoT) and industrial environments [7].”
Network Intrusion Detection Using LSTM-Based Models
Bhushan, A., Singh, A. K., & Dwivedi, V. K. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-0148-9_4
GPU Accelerated Interpretable Generalization for Scalable Network Intrusion Detection and Forensics
Huang, S.-T., Chung, W.-C., & Pai, H.-T. (2025) · IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · doi:10.1109/dasc68382.2025.00024
“The study [1] in IEEE Communications Surveys & Tutorials offers an authoritative panorama of explainable IDS: most detectors first optimize for accuracy with opaque learners and afterwards bolt on interpretability through post ‑ hoc toolkits such as SHAP and LIME.”
Analyzing the Role of LIME and SHAP in Explainable DoS Attack Detection for IoT Systems
Paul, A., Kumari, S., Navadia, N. R., & Sinha, S. (2025) · International Conference on Automation, Computing and Renewable Systems (ICACRS) · doi:10.1109/icacrs67045.2025.11324170
“The [16] shows intense review of applications of XAI for anomaly-based IDS with the IOT devices.”
XAI-ML-AMD: Explainable Machine Learning for Android Malware Detection
Aishwarya, P., & James, J. (2025) · International Conference on Software, Systems and Information Technology (SSITCON) · doi:10.1109/ssitcon66133.2025.11342139
“Malicious apps can exploit android’s permission system to steal personal data, disrupt services, monitor user activity, or even commit identity theft [4], [7].”
InfluentialEnhancing Cybersecurity using Deep Learning for Real-Time Threat Detection and Response
Mishra, S., Ahamad, A. M. K. R., Nandhini, N., Ragunath, D., Kumar, G. R., & Barath Kumar, S. (2025) · International Conference on Electronics, Communication and Aerospace Technology (ICECA) · doi:10.1109/iceca66444.2025.11382928
Amin, M. A., Ahsan, M. S., Maua, J., Eva, A. A., Mridha, M. F., & Hossen, M. J. (2026) · IEEE Open Journal of Intelligent Transportation Systems · doi:10.1109/ojits.2026.3664301
“Traditionally, in automotive cybersecurity has focused on post-hoc intrusion detection systems (IDS) that raise alerts once an attack has already begun [5].”
A Survey of Intrusion Detection Systems in Deep Learning Era: Methods and Perspectives
Berrezzek, A., Djellali, H., & Mahnane, L. (2025) · International Conference on Advances in Electronics, Control and Communication Systems (ICAECCS) · doi:10.1109/icaeccs68240.2025.11384749 · Cited by 1
“Innovations include behavioral analysis, cloud/edge deployment, FL [5] for privacy, blockchain [5] for system integrity, and explainable AI (XAI) for transparency [6].”
Riemann Adaptive Clustering Federated Model for IoT Intrusion Detection with Adversarial SamplesPreprint
Wang, Z., Su, W., Xie, H., & Li, D. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6331705
Adaptive Intrusion Detection Enhanced by Cyber Threat Intelligence
Reddy, B. R. S., Ganesh, D., Kumar, M. S., Likhitha, A., Dattudu, B. J., & Reddy, D. V. M. (2026) · International Conference on Intelligent Sustainable Systems (ICISS) · doi:10.1109/iciss67859.2026.11453603
“Moustafa et al. [17] have made an analysis of explainable intrusion detection systems of IoT, whereby SHAP and LIME methods were incorporated.”
Lv, J., & Liu, K. (2026) · Journal of Network and Systems Management · doi:10.1007/s10922-026-10043-8
Explainable and Privacy‐Aware Collaborative Optimization for Efficient and Robust IIoT Clusters
Lin, Y., & Zhong, Q. (2026) · Internet Technology Letters · doi:10.1002/itl2.70263
“Ensuring data privacy while enhancing network efficiency has become a critical issue that needs immediate attention [4].”
Mythily, S., & Meenakshi, D. C. (2026) · Journal of Wireless Mobile Networks Ubiquitous Computing and Dependable Applications · doi:10.58346/jowua.2026.i1.026
Generation of Semantic Explanations for AI-Based Models for Network Intrusion Detection
Fernández-Morales, E., Tobarra, L., Robles-Gómez, A., Pastor-Vargas, R., & Vidal-Balboa, P. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-16995-2_39
Digital twin-inspired intelligent healthcare framework for defence personnel
Ahanger, T. A., Bhatia, M., Algamdi, S. A., & Ullah, I. (2026) · Future Generation Computer Systems · doi:10.1016/j.future.2026.108516
Jhawar, V., Grover, K., Samanta, P. K., Darshana, S., Mishra, S., & Bakshi, A. (2026) · International Conference on Computing, Electronics & Communications Engineering (iCCECE) · doi:10.1109/iccece69715.2026.11493103
Rajesh, G., Anandhi, R. J., Prasad, P. B. A., Thirumalraj, A., & Gopikha, S. (2026) · IGI Global eBooks · doi:10.4018/979-8-2600-1498-1.ch010 · Cited by 1
Narasimhamu, K. L., Naveen, K., Kaliappan, S., & Velankanni, T. R. (2025) · IEEE International Conference on Recent Trends in Computing and Smart Mobility (RCSM) · doi:10.1109/rcsm67767.2025.11507742
“Deep ensembles and other opaque models can achieve strong empirical performance on large, labelled corpora but produce outputs that are difficult for operators to interpret [5], [6].”
Explainable Intrusion Detection and Prevention Framework for Next-Generation Networks
Siam, A. A., Shohan, S., Faruqui, N., & Alazab, M. (2025) · IEEE International Conference on Signal Processing, Information, Communication and Systems (SPICSCON) · doi:10.1109/spicscon69221.2025.11503950
“Although it can be useful in post-hoc analysis, most XAI-enabled IDS research is restricted to offline experimentation and traditional datasets, providing little in the way of support to actual real-time operation [19].”
Explainable Artificial Intelligence (XAI) in IoT and WSN Security: A Systematic Review
Jain, K., Kumar, S., Sapra, V., & Agarwal, A. (2026) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-026-10623-6 · Cited by 1
“Thus the classical ML evalu - ation metrics remain relevant but must be adapted to reflect imbalance, adversarial resilience, and real-time constraints unique to IoT security [ 12, 18, 41, 44].”
InfluentialReal Time Malware Detection using Explainable AI and Deep Learning
Thasleena, V. A., Narmadha, D., & Sundar, G. N. (2026) · International Conference on Smart Futuristic Technology (SMARTTECH) · doi:10.1109/icsft66733.2026.11506656
“As these attacks continue to become more sophisticated, intelligent, adaptive, and explainable mechanisms would be needed to produce fast and accurate decisions for malware detection [3].”
INTERPRETABLE AI FOR CYBER THREAT DETECTION IN SMART SYSTEMS
Abdukarimova, A. A., Ismailova, R. A., Jumagaliyeva, A., Рыстыгулова, В. Б., & Кoxegen, A. (2025) · SMART TECHNOLOGIES JOURNAL · doi:10.62687/stj.7.1.2025.14
A Federated Learning Data-Centric Explainable Framework of Trustworthy IoT Edge Intelligence
Kamalakannan, K., & Parthipan, V. (2026) · International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering (RMKMATE) · doi:10.1109/rmkmate69073.2026.11518784
Leveraging AI for Real-Time Intrusion Detection in IOT-Enabled Healthcare Systems
Butt, A., Huzaifa, M. M., Sumbal, U., & Hussain, M. Z. (2026) · International Conference on Data Science, Machine Learning, and Intelligence (DataSciMI) · doi:10.1109/datascimi67380.2026.11523932
Intelligence Defense - the Role of Artificial Intelligence in Combating Cyber Threats
OVREIU, S., Daniel, S. A. V. U., Mitan, E., & NEACȘU, D. M. (2026) · Romanian Cyber Security Journal · doi:10.54851/v8i1y202608 · Cited by 1
Vikas, C. M., Kumar, N. M. S., Kiran, C. M. L., Deep, K. S., Goutham, G., Yattinahalli, S., Dharawadmath, S. I., Shwethasree, R., & Thorve, V. P. (2026) · AIP conference proceedings · doi:10.1063/5.0341427
XAI-Enhanced Insider Risk Scoring with Adaptive Weighted Ensemble for Medium-Sized Organizations
Abu-Arqoub, M. H., Marie, R. R., & Titinchi, A. A. (2026) · International Conference on Computational Intelligence Approaches and Applications (ICCIAA) · doi:10.1109/icciaa68481.2026.11543714
“Moustafa et al. [17] argued explanations must be meaningful, timely, and actionable—embedded in dashboards rather than post hoc.”
Naaz, H., & Ajmera, R. (2026) · International Conference on Recent Trends in Computer Science and Technology (ICRTCST) · doi:10.1109/icrtcst68392.2026.11545449
“Moustafa and colleagues [1] pioneered explainable intrusion detection (XAI-IDS) frameworks in a way that is targeted to the Internet of Things (IoT), in this way establishing the interpretability benchmarks in cyber-defense.”
InfluentialGao, Y., Yin, S., Laghari, A. A., Kryvinska, N., Hejaili, A. A., & Gadekallu, T. R. (2026) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2026.3702744
“For time t , a one-dimensional convolution with step size 1 and convolution kernel size 3 is used to compute the query matrix Q and the key matrix K , and the calculation of the value matrix V is the same as the calculation of equations (8,9,10).”
A Hybrid Bio-Inspired Deep Learning Framework for Adaptive Web Threat Detection
Avanija, J., Mounika, S. S., Khan, B. M. O., Kumar, G. P., & Chandra, T. P. (2026) · International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV) · doi:10.1109/icicv68925.2026.11554841
“Moreover, the trend in recent studies is towards adaptive and explainable intrusion detection systems to enhance reliability and trust in cybersecurity application [13], [20].”
Jayalakshmi, R., Pavanathil, R. J., Chowdary, S., Janardhanan, J., Hari, P., & Srinivasan, R. (2026) · ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS) · doi:10.1109/icetsis68266.2026.11548832
“The absence of timely and correct domain articulation is a huge limitation [13].”
Interpretable and robust intrusion detection: A hybrid CBAM-CNN model with XAI techniques
Bello, S. A., Binbeshr, F., Ibrahimi, K., Shinwari, M. W., Imam, M., & Mahmoud, A. S. H. (2026) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2026.111348
Explainable Lightweight Deep Learning for Secure Edge Anomaly Detection
Al-Shaher, M. A. (2026) · Journal of Internet Services and Information Security · doi:10.58346/jisis.2026.i2.012
HARMONI: A Two-Stage Hybrid Learning Framework with Dynamic Metric Learning for Interpretable NIDS
Hu, R., Zhang, Z., Li, M., Wen, Y., & Wang, L. (2026) · Applied Sciences · doi:10.3390/app16136538
Rharif, A., Charafi, Z., Zaydi, M., Belkhala, S., & Maleh, Y. (2026) · Research Square · doi:10.21203/rs.3.rs-9929399/v1
kaur, G., Saini, R., Somasundaram, R., Sarkar, R., Sathyakala, S., & Manimegalai, V. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-23297-7_29
Opening the Black Box: Explainable AI in Network Intrusion Detection
Joya, S. G., & Sultana, N. (2026) · Management Studies · doi:10.17265/2328-2185/2026.03.004
Cyberthreat Forensics Using AI-Neutrosophic Reasoning for SQL Injection Detection in WebApplications
Alghamdi, A. A. (2026) · Journal of Soft Computing and Data Mining · doi:10.30880/jscdm.2026.07.02.022
Kumar, A., & Thing, V. L. L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.12203
“Explanation In [23], authors argue that many XAI methods produce low-level explanations, typically in the form of numerical feature importance vectors.”
Ahmed, U., Muhammad, S., Muhammad, H. G., Choi, J., & Aleem, S. M. (2026) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-026-01426-5
“…Convolutional Neural Networks (CNNs) have been able to provide very accurate results when detecting anomalies in IoT devices; however, due to the black box nature of these models, they are limited in use by security teams within large-scale IoT environments where explanations are required [11–13].”
Advanced AI Techniques for Intrusion Detection and Privacy Preservation in Autonomous Ecosystems
Sharma, V., Vashishth, T. K., Teotia, S., Singh, N. P., Shah, S., Chaudhary, S., & Verma, P. K. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-2600-3070-7.ch008
Explainable Trust Calibration Framework for AI-Driven Intrusion Detection Systems
Anand, S., & Singh, A. (2026) · International Conference on Secure Cyber Computing and Communications (ICSCCC) · doi:10.1109/icsccc69031.2026.11600331
Li, Z., & Yao, W. (2026) · Neural Networks · doi:10.1016/j.neunet.2026.109398
Dupad, C., Dupad, T. K., & Havaragi, T. (2026) · International Conference on Innovations in Cybersecurity and Data Science (ICICDS) · doi:10.1109/icicds70526.2026.11604619
“Moustafa et al. [13] presented a comprehensive survey highlighting the importance of explainable intrusion detection for enhancing trust, interpretability, and regulatory compliance in IoT security.”
Zhang, K. (2026) · International Conference on Algorithms, Software Engineering and Network Security (ASENS) · doi:10.1109/asens69964.2026.11605335
“This module is based on an improved channel attention mechanism, introducing a perturbation response coefficient to optimize attention weight allocation, thereby achieving accurate localization of minor adversarial perturbations [7].”
Residual Observability and Attack Detectability in Encrypted OPC UA TrafficPreprint
Ha, S. S., Foerster, F., Beuster, H., Zeller, E., Merli, D., & Scholl, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.17809 · Cited by 1
“A complementary research direction uses feature importance and explainable artificial intelligence to analyze how trained IDS models use their inputs [10, 11, 12].”
Utilizing Fuzzy AI to Find Relative Desirability of Online Threats on Social Media
Khanum, S., & Firos, A. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-8292-0.ch009
Gunupudi, C., Kondapalli, K. K., & Reddy, N. (2026) · International Conference on Computer Networks, Big Data and IoT (ICCBI) · doi:10.1109/iccbi68589.2026.11619897
“Open research gaps in explainability, operational scalability, and provable regulatory conformance continue to motivate domain-tailored framework design [9], [11], [12], [14], [16].”
Explanation-Surface Governance in XAI-Enabled Network Intrusion Detection under Resource ConstraintsPreprint
Le, T. D., Dinh, T. D., Hao, P., & Pham, V. D. (2026) · Research Square · doi:10.21203/rs.3.rs-9800570/v1
Automated Security Compliance Reporting of Internet of Things Devices: A Literature Review
Rahman, W., Ray, B., & Islam, N. (2026) · IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM) · doi:10.1109/wowmom69805.2026.00046
Sharmila, A. H., & Deepanramkumar, P. (2026) · Array · doi:10.1016/j.array.2026.101114
An Explainable Lightweight MLP-Based Framework for Zero-Day Intrusion Detection
Bhowmik, S., Pal, J., Amitabh, K., Dutta, S., Roy, S., & Dash, S. K. (2026) · IEEE Global Symposium on Emerging and Communication Technologies (GSEACT) · doi:10.1109/gseact68539.2026.11620364
“Explainable machine learning models have been used for anomaly detection situations, advanced persistent threats, and IoT botnet detection [17-20].”
Ghanem, M. C. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7246621
Hassan, J., Abdullah, M., & Aljeaid, D. (2026) · Frontiers in Computer Science · doi:10.3389/fcomp.2026.1840175
Hussain, R. (2026) · International Journal of Engineering Technology Research & Management · doi:10.67809/ijetrm.1787494112
Explainable Machine Learning for DDoS Attack Detection with Physical Network Validation
Anshori, M. A., & Amri, R. (2026) · Journal of Computer Science Application and Engineering · doi:10.70356/josapen.v4i2.131
“The first is the “black - box” problem, i.e., the limited transparency of model decisions [8].”
Enabling Latent-Space Alignment for Robust Multi-Class Attack Detection in IoT Environments
Adjei, J. A., Zincir-Heywood, N., Heywood, M. I., Nandy, B., & Seddigh, N. (2026) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms69089.2026.11668315
“Moreover, traditional signature-based Network Intrusion Detection Systems (NIDS) have become less effective in coping with zero-day exploits, polymorphic malware, and adversarial manipulation, particularly in resource-limited and heterogeneous IoT environments [1], [2].”
Metadata
- Authors
- Moustafa, N., Koroniotis, N., Keshk, M., Zomaya, A. Y., & Tari, Z.
- Affiliations
- UNSW Sydney (AU)
- The University of Sydney (AU)
- RMIT University (AU)
- Venue
- IEEE Communications Surveys & Tutorials
- Published
- 2023
- Volume
- 25
- Issue
- 3
- Pages
- 1775-1807
- ISSN
- 1553-877X (ISSN-L)
- 2373-745X
- OpenAlex
- W4378365142
- Cited by
- 266
- References
- 187
- Citations by year
- 2026: 70 · 2025: 110 · 2024: 71 · 2023: 15
- FWCI
- 29.55
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Communications Surveys & Tutorials (publishedVersion)
- Figshare (submittedVersion)
- Funders
- Australian Research Council’s Discovery Early Career Researcher Award (DE230100116)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- explainable AI, intrusion detection, Internet of Things security, anomaly-based intrusion detection, cyber defense, interpretability, deep learning anomaly detection, attack detection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.