Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research
Open accessThe DOI matches its Crossref record; 262 of the 262 references it cites were found in a registry or an index.
Abstract
This survey presents a comprehensive review of current literature on Explainable Artificial Intelligence (XAI) methods for cyber security applications. Due to the rapid development of Internet-connected systems and Artificial Intelligence in recent years, Artificial Intelligence including Machine Learning and Deep Learning has been widely utilized in the fields of cyber security including intrusion detection, malware detection, and spam filtering. However, although Artificial Intelligence-based approaches for the detection and defense of cyber attacks and threats are more advanced and efficient compared to the conventional signature-based and rule-based cyber security strategies, most Machine Learning-based techniques and Deep Learning-based techniques are deployed in the “black-box” manner, meaning that security experts and customers are unable to explain how such procedures reach particular conclusions. The deficiencies of transparencies and interpretability of existing Artificial Intelligence techniques would decrease human users’ confidence in the models utilized for the defense against cyber attacks, especially in current situations where cyber attacks become increasingly diverse and complicated. Therefore, it is essential to apply XAI in the establishment of cyber security models to create more explainable models while maintaining high accuracy and allowing human users to comprehend, trust, and manage the next generation of cyber defense mechanisms. Although there are papers reviewing Artificial Intelligence applications in cyber security areas and the vast literature on applying XAI in many fields including healthcare, financial services, and criminal justice, the surprising fact is that there are currently no survey research articles that concentrate on XAI applications in cyber security. Therefore, the motivation behind the survey is to bridge the research gap by presenting a detailed and up-to-date survey of XAI approaches applicable to issues in the cyber security field. Our work is the first to propose a clear roadmap for navigating the XAI literature in the context of applications in cyber security.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures














Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“As a result, Artificial Intelligence (AI) has become integral to domains such as healthcare, finance, and particularly cybersecurity, where the ability to process complex, high-velocity data streams is critical (Zhang et al., 2022).”
From Explainable AI: enhancing decision-making in the detection of cyber threats (2026) · cites this paper as Zhang et al., 2022
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Our findings confirm the growing importance of XAI, with SHAP and LIME increasingly used to provide feature-level insights [40].”
From Application of Machine Learning and Deep Learning Techniques for Enhanced Insider Threat Detection in Cybersecurity: Bibliometric Review (2025) · cites this paper as [40]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Zhang et al. (2022) argue that developing more generic, quantifiable, and standardized frameworks is critical for benchmarking XAI applications in cybersecurity.”
From Explainable AI: enhancing decision-making in the detection of cyber threats (2026) · cites this paper as Zhang et al. (2022)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
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
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 2×
“Users and specialists can understand the logical explanation and main data evidence due to XAI's contribution of interoperability to the results produced by the AI-based statistical models [19].”
BackgroundBarredo 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 · cited 3×
“CATEGORIZATIONS OF XAI According to [53], [54], the XAI categories can be structured in a variety of aspects shown in Figure 6.”
BackgroundBidirectional recurrent neural networks
Schuster, M., & Paliwal, K. K. (1997) · IEEE Transactions on Signal Processing · doi:10.1109/78.650093 · Cited by 10,172 · cited 2×
“Several models 826 including CNN-GRU [172], BiRNN [173], and BiRNN- 827 Attention [174] were used and tested on this dataset 828 whereas explainability-based metrics such as Intersection- 829 Over-Union (IOU), comprehensiveness, and sufficiency were 830 utilized to evaluate the model interpretability.”
MethodVision meets robotics: The KITTI dataset
Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913491297 · Cited by 9,913 · cited 1×
“[139] KITTI 2013 5831 A cutting-edge dataset obtained from a Volkswagen station wagon for use in studies on mobile robotics and autonomous driving.”
BackgroundMIMIC-III, a freely accessible critical care database
Johnson, A. E. W., Pollard, T. J., Shen, L., Lehman, L.-W. H., Feng, M., Ghassemi, M., Moody, B., Szolovits, P., Anthony Celi, L., & Mark, R. G. (2016) · Scientific Data · doi:10.1038/sdata.2016.35 · Cited by 8,141
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01228-7 · Cited by 6,909 · cited 1×
“Shapley Additive Explanations (SHAP) tools [59], Saliency Map [60], and Gradient-weighted Class Activation Mapping (Grad-CAM) [61] are widely used model-agnostic explanation tools.”
Method
Research works printed but not linked: 28
- 3. "Number of internet users worldwide 2021," Statista. https://www.statista.com/statistics/273018/number-of-internet-users- worldwide/ (accessed Jul. 01, 2022).
- 4. "2021 Cyber Attack Trends Mid-Year Report | Check Point Software." https://pages.checkpoint.com/cyber-attack-2021- trends.html (accessed Jul. 01, 2022).
- 23. R. A. Alves and D. Costa, "A Survey of Random Forest Based Methods for Intrusion Detection Systems," ACM Computing Surveys (CSUR), May 2018, doi: 10.1145/3178582. · DOI · Paper page
- 2012, 14:00-17:00
- 38. "Cybersecurity Market worth $345.4 billion by 2026." https://www.marketsandmarkets.com/PressReleases/cyber- security.asp (accessed Jul. 05, 2022).
- 40. O. Biran and C. V. Cotton, "Explanation and Justification in Machine Learning : A Survey Or," undefined, 2017, Accessed: Jul. 08, 2022. [Online]. Available: https://www.semanticscholar.org/paper/Explanation-and- Justification-in-Machine-Learning-%3A-Biran- Cotton/02e2e79a77d8aabc1af1900ac80ceebac20abde4
- 46. "Black Box Attacks on Explainable Artificial Intelligence(XAI) methods in Cyber Security | IEEE Conference Publication | IEEE Xplore." https://ieeexplore.ieee.org/abstract/document/9206780 (accessed Jul. 08, 2022). · DOI · Paper page
- 51. "What is GDPR, the EU's new data protection law?," GDPR.eu, Nov. 07, 2018. https://gdpr.eu/what-is-gdpr/ (accessed Jul. 08, 2022).
- 78. C. Mars, R. Dès, and M. Boussard, "The three stages of Explainable AI: How explainability facilitates real world deployment of AI," Jan. 2020.
- 99. "VirusShare.com." https://virusshare.com/ (accessed Jul. 13, 2022).
- 101. "Drebin: Effective and Explainable Detection of Android Malware in Your Pocket -NDSS Symposium." https://www.ndss- symposium.org/ndss2014/programme/drebin-effective-and- explainable-detection-android-malware-your-pocket/ (accessed Jul. 13, 2022). · DOI · Paper page
- 135. 134PDFFast Global Alignment Kernels | Semantic Scholar." https://www.semanticscholar.org/paper/Fast-Global-Alignment- Kernels-Cuturi/7de1f5079ed7a8a8a5690f72ad2099f52d697393 (accessed Jul. 14, 2022).
- 156. E. Raff, J. Barker, J. Sylvester, R. Brandon, B. Catanzaro, and C. K. Nicholas, "Malware Detection by Eating a Whole EXE," Jun. 2018. Accessed: Jul. 18, 2022. [Online]. Available: https://www.aaai.org/ocs/index.php/WS/AAAIW18/paper/view/164 22
- 157. H. S. Anderson and P. Roth, "EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models." arXiv, Apr. 16, 2018. doi: 10.48550/arXiv.1804.04637. · DOI
- 159. A. Yan et al., "Effective detection of mobile malware behavior based on explainable deep neural network," Neurocomputing, vol. 453, pp. 482-492, Sep. 2021, doi: 10.1016/j.neucom.2020.09.082. · DOI
- 165. 164"Daily number of e-mails worldwide 2025," Statista. https://www.statista.com/statistics/456500/daily-number-of-e-mails- worldwide/ (accessed Feb. 21, 2022).
- 168. M. Renftle, H. Trittenbach, M. Poznic, and R. Heil, "Explaining Any ML Model? --On Goals and Capabilities of XAI," Jun. 2022, doi: 10.48550/arXiv.2206.13888. · DOI
- 181. "MAWI Working Group Traffic Archive." http://mawi.wide.ad.jp/mawi/ (accessed Jul. 19, 2022).
- 187. J. Gee and P. M. Button, "The Financial Cost of Fraud 2019," p. 28.
- 189. "IEEE-CIS Fraud Detection." https://kaggle.com/competitions/ieee- fraud-detection (accessed Jul. 20, 2022).
- 212. S. Mane and D. Rao, "Explaining Network Intrusion Detection System Using Explainable AI Framework." arXiv, Mar. 12, 2021. doi: 10.48550/arXiv.2103.07110. · arXiv · doi:10.48550/arxiv.2103.07110 · Paper page
- 222. 221"Home -eduroam.org," eduroam.org -eduroam global site. https://eduroam.org/ (accessed Jul. 23, 2022).
- 228. 227"KDD Cup 1999 Data." http://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html (accessed Jul. 23, 2022).
- 232. D. Dave, H. Naik, S. Singhal, and P. Patel, "Explainable AI meets Healthcare: A Study on Heart Disease Dataset." arXiv, Nov. 06, 2020. doi: 10.48550/arXiv.2011.03195. · arXiv · doi:10.48550/arxiv.2011.03195 · Paper page
- 258. "VeReMi dataset," VeReMi-dataset.github.io. https://veremi- dataset.github.io/ (accessed Jul. 26, 2022).
- 265. J. L. Mattu Julia Angwin,Lauren Kirchner,Surya, "How We Analyzed the COMPAS Recidivism Algorithm," ProPublica. https://www.propublica.org/article/how-we-analyzed-the-compas- recidivism- algorithm?token=BqO_ITYNAKmQwhj7daSusnn7aJDGaTWE (accessed Jul. 27, 2022).
- 270. D. Becking, M. Dreyer, W. Samek, K. Müller, and S. Lapuschkin, "ECQ$$^{\text {x}}$$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs," in xxAI -Beyond Explainable AI: International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers, A.
- 272. W. Ha, C. Singh, F. Lanusse, S. Upadhyayula, and B. Yu, "Adaptive wavelet distillation from neural networks through interpretations," in Advances in Neural Information Processing Systems, 2021, vol. 34, pp. 20669-20682. Accessed: Jul. 29, 2022. [Online]. Available: https://proceedings.neurips.cc/paper/2021/hash/acaa23f71f963e96c8 847585e71352d6-Abstract.html
Cited by
A literature review on applications of explainable artificial intelligence (XAI)
Kalasampath, K., Spoorthi, K. N., Sajeev, S., Kuppa, S. S., Ajay, K., & Maruthamuthu, A. (2025) · IEEE Access · doi:10.1109/access.2025.3546681 · Cited by 180
“Zhang et al. [88] endorse SHAP for malware detection, revealing feature importance to clarify model decisions.”
A survey on explainable artificial intelligence for cybersecurity
Rjoub, G., Bentahar, J., Abdel Wahab, O., Mizouni, R., Song, A., Cohen, R., Otrok, H., & Mourad, A. (2023) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2023.3282740 · Cited by 158
An assessment framework for explainable AI with applications to cybersecurity
Calzarossa, M. C., Giudici, P., & Zieni, R. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11141-w · Cited by 40
Explainable AI: enhancing decision-making in the detection of cyber threats
Prasad, P. W. C., Sayeed, M. S., Nguyen, D.-M., Hutabarat, D. P., & Mohiuddin, G. M. (2026) · Frontiers in Computer Science · doi:10.3389/fcomp.2026.1762332 · Cited by 16
Ofori, H. K., Bell-Dzide, K., Brown-Acquaye, W. L., Lempogo, F., Frimpong, S. O., Agbehadji, I. E., & Millham, R. C. (2025) · Symmetry · doi:10.3390/sym17101704 · Cited by 7
A brief Review on the Role of Context in Explainable AI
Baruah, R. D., & Organero, M. M. (2024) · 2024 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS) · doi:10.1109/eais58494.2024.10570037 · Cited by 2
“Various other surveys on XAI are focused towards specific domains such as healthcare [23], industry [24], cyber-security [25], and finance [26].”
BackgroundMohamed, 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
Metadata
- Authors
- Zhang, Z., Hamadi, H. A., Damiani, E., Yeun, C. Y., & Taher, F.
- Affiliations
- Khalifa University of Science and Technology (AE)
- Zayed University (AE)
- Venue
- IEEE Access
- Published
- 2022
- Volume
- 10
- Pages
- 93104-93139
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W4295854586
- Cited by
- 450
- References
- 262
- Citations by year
- 2026: 118 · 2025: 160 · 2024: 109 · 2023: 62
- FWCI
- 27.23
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- explainable AI, cybersecurity, intrusion detection, malware detection, spam filtering, black-box models, model interpretability, trust in AI, cyber defense, explainable machine learning
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.