CoChat

Explainable artificial intelligence for cybersecurity: a literature survey

Open access

The DOI matches its Crossref record; 113 of the 114 references it cites were found in a registry or an index.

Abstract

Abstract With the extensive application of deep learning (DL) algorithms in recent years, e.g., for detecting Android malware or vulnerable source code, artificial intelligence (AI) and machine learning (ML) are increasingly becoming essential in the development of cybersecurity solutions. However, sharing the same fundamental limitation with other DL application domains, such as computer vision (CV) and natural language processing (NLP), AI-based cybersecurity solutions are incapable of justifying the results (ranging from detection and prediction to reasoning and decision-making) and making them understandable to humans. Consequently, explainable AI (XAI) has emerged as a paramount topic addressing the related challenges of making AI models explainable or interpretable to human users. It is particularly relevant in cybersecurity domain, in that XAI may allow security operators, who are overwhelmed with tens of thousands of security alerts per day (most of which are false positives), to better assess the potential threats and reduce alert fatigue. We conduct an extensive literature review on the intersection between XAI and cybersecurity. Particularly, we investigate the existing literature from two perspectives: the applications of XAI to cybersecurity (e.g., intrusion detection, malware classification), and the security of XAI (e.g., attacks on XAI pipelines, potential countermeasures). We characterize the security of XAI with several security properties that have been discussed in the literature. We also formulate open questions that are either unanswered or insufficiently addressed in the literature, and discuss future directions of research.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s12243-022-00926-7

Cites

113 of 114 references verified0 citation errors · 1 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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?

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

Show all 114 references

Research works printed but not linked: 23

  1. Adebayo J et al (2018) Sanity checks for saliency maps. In: Advances in neural information processing systems, p 31
  2. Anders C et al (2020) Fairwashing explanations with off-mani- fold detergent. In: International conference on machine learning. PMLR, pp 314-323
  3. Boopathy A et al (2020) Proper network interpretability helps adversarial robustness in classification. In: International con- ference on machine learning. PMLR, pp 1014-102
  4. Deng J et al (2009) Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. Ieee, pp 248-255 · DOI · Paper page
  5. Deng J et al (2009) Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. Ieee, pp 248-255 · DOI · Paper page
  6. Dimanov B et al (2020) You Shouldn't Trust Me: Learning models which conceal unfairness from multiple explanation methods. In: SafeAI@AAAI
  7. Dombrowski A-K et al (2019) Explanations can be manipulated and geometry is to blame. In: Advances in neural information processing systems, p 32
  8. Elson J et al (2007) Asirra: A CAPTCHA that exploits inter- est-aligned manual image categorization. In: CCS, vol 7, pp 366-374
  9. Heo J, Joo S, Moon T (2019) Fooling neural network interpreta- tions via adversarial model manipulation. In: Advances in neural information processing systems, p 32
  10. Hong S et al (2015) Online tracking by learning discriminative saliency map with convolutional neural network. In: International conference on machine learning. PMLR, pp 597-606
  11. Hooker S et al (2019) A benchmark for interpretability methods in deep neural networks. In: Advances in neural information pro- cessing systems, p 32
  12. Kleinbaum DG et al (2002) Logistic regression. Springer, New York
  13. Krizhevsky A, Hinton G et al (2009) Learning multiple layers of features from tiny images 65. Kuppa A, Le-Khac N-A (2021) Adversarial xai methods in cyber- security. In: IEEE transactions on information forensics and secu- rity, vol 16, pp 4924-4938
  14. Lundberg SM, Lee S-I (2017) A unified approach to interpreting model predictions. In: Advances in neural information processing systems, p 30
  15. Miura T, Hasegawa S, Shibahara T (2021) MEGEX: Data-free model extraction attack against gradient-based explainable AI. In: arXiv:2107.08909 · arXiv
  16. Moustafa N (2019) New generations of internet of things datasets for cybersecurity applications based machine learning: TON IoT datasets. In: Proceedings of the eResearch Australasia Conference. Brisbane, Australia, pp 21–25
  17. Netzer Y et al (2011) Reading digits in natural images with unsupervised feature learning. In: NIPS workshop on deep learning and unsupervised feature learning, p 2011
  18. Rish I et al (2001) An empirical study of the naive Bayes classifier. In: IJCAI 2001 workshop on empirical methods in artificial intelligence, vol 3, pp 41–46
  19. Slack DZ et al (2021) Reliable Post hoc Explanations: Mod- eling Uncertainty in Explainability. In: Beygelzimer A et al (eds) Advances in neural information processing systems. https:// openr eview. net/ forum? id= rqfq0 CYIekd. Accessed 01 Aug 2022 117.
  20. Slack D et al (2021) Counterfactual explanations can be manipu- lated. In: Advances in neural information processing systems, vol 34, pp 62-75 118.
  21. Wang Z et al (2020) Smoothed geometry for robust attribution. In: Advances in neural information processing systems, vol 33, pp 13623-13634 135.
  22. Zhang X et al (2020) Interpretable deep learning under fire. In: 29th fUSENIXg Security Symposium (fUSENIXg Security 20) 140.
  23. Zhao X et al (2021) BayLIME: Bayesian local interpretable model-agnostic explanations. In: UAI 141.

Cited by

See all 266

Metadata

Authors
Charmet, F., Tanuwidjaja, H. C., Ayoubi, S., Gimenez, P.-F., Han, Y., Jmila, H., Blanc, G., Takahashi, T., & Zhang, Z.
Affiliations
  • National Institute of Information and Communications Technology (JP)
  • Laboratoire Lorrain de Recherche en Informatique et ses Applications (FR)
  • Institut de Recherche en Informatique et Systèmes Aléatoires (FR)
  • Institut national de recherche en sciences et technologies du numérique (FR)
  • Institut Polytechnique de Paris (FR)
  • Huawei Technologies (France) (FR)
Corresponding author
Charmet, Fabien
Venue
Annals of Telecommunications
Published
2022-10-26
Volume
77
Issue
11-12
Pages
789-812
ISSN
  • 0003-4347 (ISSN-L)
  • 1958-9395
OpenAlex
W4307571902
Cited by
167
References
99
Citations by year
2026: 62 · 2025: 52 · 2024: 35 · 2023: 18
FWCI
8.64
Type
journal article
Language
en
Open access
Licence
Locations
  • Annals of Telecommunications (publishedVersion, cc-by)
  • HAL (submittedVersion, other-oa)
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 › Computer Networks and Communications › Network Security and Intrusion Detection
Keywords
explainable AI, cybersecurity, model interpretability, intrusion detection, malware classification, Android malware detection, security alerts, false positives, alarm fatigue

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: Explainable artificial intelligence for cybersecurity: a literature survey. https://app.cochat.ai/papers/10.1007/s12243-022-00926-7
The paper
Charmet, F., Tanuwidjaja, H. C., Ayoubi, S., Gimenez, P.-F., Han, Y., Jmila, H., Blanc, G., Takahashi, T., & Zhang, Z. (2022). Explainable artificial intelligence for cybersecurity: a literature survey. Annals of Telecommunications. https://doi.org/10.1007/s12243-022-00926-7

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.