An assessment framework for explainable AI with applications to cybersecurity
Open accessThe DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Abstract
Several explainable AI methods are available, but there is a lack of a systematic comparison of such methods. This paper contributes in this direction, by providing a framework for comparing alternative explanations in terms of complexity and robustness. We exemplify our proposal on a real case study in the cybersecurity domain, namely, phishing website detection. In fact, in this domain explainability is a compelling issue because of its potential benefits for the detection of fraudulent attacks and for the design of efficient security defense mechanisms. For this purpose, we apply our methodology to the machine learning models obtained by analyzing a publicly available dataset containing features extracted from malicious and legitimate web pages. The experiments show that our methodology is quite effective in selecting the explainability method which is, at the same time, less complex and more robust.
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
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
“Calzarossa et al. (2025) compared explainability techniques across security applications, highlighting trade-offs between robustness and usability.”
From Explainable AI: enhancing decision-making in the detection of cyber threats (2026) · cites this paper as Calzarossa et al. (2025)
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
“First, the diversity of XAI techniques such as SHAP, LIME, or gradient-based methods creates inconsistency in evaluation, as no universally accepted benchmarks exist (Calzarossa et al., 2025).”
From Explainable AI: enhancing decision-making in the detection of cyber threats (2026) · cites this paper as Calzarossa et al., 2025
Experimental — accuracy not yet measured
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
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
Explanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302
A Survey on the Explainability of Supervised Machine Learning
Burkart, N., & Huber, M. F. (2021) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.12228 · Cited by 1,008
Explainable artificial intelligence: a comprehensive review
Minh, D., Wang, H. X., Li, Y. F., & Nguyen, T. N. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10088-y · Cited by 983
Machine learning based phishing detection from URLs
Sahingoz, O. K., Buber, E., Demir, O., & Diri, B. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.09.029 · Cited by 857
A Survey of Methods for Explaining Black Box Models
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., & Pedreschi, D. (2019) · ACM Computing Surveys · doi:10.1145/3236009 · Cited by 629 · cited 1×
“Nevertheless, the extant literature relies on the regulatory defi - nition, such as that reported in Bracke et al. (2019), for which explainability requires an explicit understanding of the factors which determine a given machine learning output (see also Guidotti et al. (2018)).”
A framework for detection and measurement of phishing attacks
Garera, S., Provos, N., Chew, M., & Rubin, A. D. (2007) · Proceedings of the 2007 ACM workshop on Recurring malcode · doi:10.1145/1314389.1314391 · Cited by 489
Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research
Zhang, Z., Hamadi, H. A., Damiani, E., Yeun, C. Y., & Taher, F. (2022) · IEEE Access · doi:10.1109/access.2022.3204051 · Cited by 450
A comprehensive survey of AI-enabled phishing attacks detection techniques
Basit, A., Zafar, M., Liu, X., Javed, A. R., Jalil, Z., & Kifayat, K. (2021) · Telecommunication Systems · doi:10.1007/s11235-020-00733-2 · Cited by 429
Explainable Artificial Intelligence in CyberSecurity: A Survey
Capuano, N., Fenza, G., Loia, V., & Stanzione, C. (2022) · IEEE Access · doi:10.1109/access.2022.3204171 · Cited by 330
Research works printed but not linked: 2
- Lorenz M (1905) Methods of measuring the concentration of wealth. Publ Am Stat Assoc 9(70):209–219
- Lundberg SM, Lee S-I (2017) A unified approach to interpreting model predictions. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Proceedings of the 31st international conference on neural information processing systems (NIPS). Curran Associates, New York, pp. 4768–4777
Cited by
Khan, F. S., Mazhar, S. S., Mazhar, K., AlSaleh, D., & Mazhar, A. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11215-9 · Cited by 150
Çil, A. E., & Yıldız, K. (2025) · Internet of Things · doi:10.1016/j.iot.2025.101696 · Cited by 37
A review on real-time plant monitoring sensors for smart agriculture
Bai, Y., Liao, Z., Shang, J., Gan, W., Kong, X., & Wei, X. (2025) · Chemical Engineering Journal · doi:10.1016/j.cej.2025.168868 · Cited by 17
How robust are ensemble machine learning explanations?
Calzarossa, M. C., Giudici, P., & Zieni, R. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.129686 · Cited by 10
Self-citationMaqbool, M., & Qureshi, I. H. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-025-01018-0 · Cited by 7
Metadata
- Authors
- Calzarossa, M. C., Giudici, P., & Zieni, R.
- Affiliations
- University of Pavia (IT)
- Corresponding author
- Zieni, Rasha
- Venue
- Artificial Intelligence Review
- Published
- 2025-02-27
- Volume
- 58
- Issue
- 5
- ISSN
- 0269-2821 (ISSN-L)
- 1573-7462
- OpenAlex
- W4408006173
- Cited by
- 40
- References
- 33
- Citations by year
- 2026: 26 · 2025: 14
- FWCI
- 16.04
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Artificial Intelligence Review (publishedVersion, cc-by)
- Funders
- Università degli Studi di Pavia
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Keywords
- explainable AI, explanation complexity, explanation robustness, phishing website detection, cybersecurity, machine learning model interpretability, malicious web pages
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: An assessment framework for explainable AI with applications to cybersecurity. https://app.cochat.ai/papers/10.1007/s10462-025-11141-w
- The paper
- Calzarossa, M. C., Giudici, P., & Zieni, R. (2025). An assessment framework for explainable AI with applications to cybersecurity. Artificial Intelligence Review. https://doi.org/10.1007/s10462-025-11141-w
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.