{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T13:56:42Z","timestamp":1783605402898,"version":"3.55.0"},"reference-count":143,"publisher":"Springer Science and Business Media LLC","issue":"11-12","license":[{"start":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T00:00:00Z","timestamp":1666742400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T00:00:00Z","timestamp":1666742400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Ann. Telecommun."],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>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.<\/jats:p>","DOI":"10.1007\/s12243-022-00926-7","type":"journal-article","created":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T05:03:21Z","timestamp":1666760601000},"page":"789-812","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":122,"title":["Explainable artificial intelligence for cybersecurity: a literature survey"],"prefix":"10.1007","volume":"77","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6926-9620","authenticated-orcid":false,"given":"Fabien","family":"Charmet","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harry Chandra","family":"Tanuwidjaja","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Solayman","family":"Ayoubi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pierre-Fran\u00e7ois","family":"Gimenez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufei","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Houda","family":"Jmila","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gregory","family":"Blanc","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takeshi","family":"Takahashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zonghua","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,26]]},"reference":[{"key":"926_CR1","unstructured":"2018 reform of EU data protection rules. European Commission. May 25, 2018 (visited on 07\/25\/2022). https:\/\/ec.europa.eu\/info\/sites\/default\/files\/data-protection-factsheet-changes_en.pdf"},{"key":"926_CR2","doi-asserted-by":"publisher","unstructured":"Adadi A, Berrada M (2018) Peeking inside the black-box: A survey on explainable artificial intelligence (XAI). In: IEEE Access, vol 6, pp 52138\u201352160. https:\/\/doi.org\/10.1109\/ACCESS.2018.2870052","DOI":"10.1109\/ACCESS.2018.2870052"},{"key":"926_CR3","unstructured":"Adebayo J et al (2018) Sanity checks for saliency maps. In: Advances in neural information processing systems, p 31"},{"key":"926_CR4","doi-asserted-by":"crossref","unstructured":"Aguilar DL et al (2022) Towards an interpretable autoencoder: A decision tree-based autoencoder and its application in anomaly detection. In: IEEE transactions on dependable and secure computing","DOI":"10.1109\/TDSC.2022.3148331"},{"key":"926_CR5","doi-asserted-by":"crossref","unstructured":"Ahmad MW, Reynolds J, Rezgui Y (2018) Predictive modelling for solar thermal energy systems: A comparison of support vector regression, random forest, extra trees and regression trees. In: Journal of cleaner production, vol 203, pp 810\u2013821","DOI":"10.1016\/j.jclepro.2018.08.207"},{"key":"926_CR6","doi-asserted-by":"publisher","unstructured":"Ahmed M et al (eds) (2022) Explainable artificial intelligence for Cyber security. Springer International Publishing, Berlin. https:\/\/doi.org\/10.1007\/978-3-030-96630-0","DOI":"10.1007\/978-3-030-96630-0"},{"key":"926_CR7","unstructured":"A\u00efvodji U et al (2019) Fairwashing: the risk of rationalization. In: arXiv:1901.09749"},{"key":"926_CR8","doi-asserted-by":"crossref","unstructured":"Alenezi R, Ludwig SA (2021) Explainability of cybersecurity threats data using SHAP. In: 2021 IEEE symposium series on computational intelligence (SSCI). IEEE, pp 01\u201310","DOI":"10.1109\/SSCI50451.2021.9659888"},{"key":"926_CR9","doi-asserted-by":"crossref","unstructured":"Alqaraawi A et al (2020) Evaluating saliency map explanations for convolutional neural networks: a user study. In: Proceedings of the 25th international conference on intelligent user interfaces, pp 275\u2013285","DOI":"10.1145\/3377325.3377519"},{"key":"926_CR10","unstructured":"Anders C et al (2020) Fairwashing explanations with off-manifold detergent. In: International conference on machine learning. PMLR, pp 314\u2013323"},{"key":"926_CR11","doi-asserted-by":"crossref","unstructured":"Antwarg L et al (2021) Explaining anomalies detected by autoencoders using Shapley additive explanations. In: Expert systems with applications, vol 186, p 115736","DOI":"10.1016\/j.eswa.2021.115736"},{"key":"926_CR12","doi-asserted-by":"crossref","unstructured":"Arp D et al (2014) Drebin: Effective and explainable detection of android malware in your pocket. In: Ndss, vol 14, pp 23\u201326","DOI":"10.14722\/ndss.2014.23247"},{"key":"926_CR13","doi-asserted-by":"crossref","unstructured":"Arrieta AB et al (2020) Explainable artificial intelligence (XAI): Concepts, Taxonomies, Opportunities and challenges toward responsible AI. In: Inf Fusion, vol 58, pp 82\u2013115","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"926_CR14","unstructured":"Asuncion A, Newman D (2007) UCI machine learning repository. Accessed: 2022-03-25. http:\/\/archive.ics.uci.edu\/ml"},{"key":"926_CR15","doi-asserted-by":"crossref","unstructured":"Bach S et al (2015) On pixel-wise explanations for non-linear classifer decisions by layerwise relevance propagation. In: PloS One, vol 10.7, p e0130140","DOI":"10.1371\/journal.pone.0130140"},{"key":"926_CR16","doi-asserted-by":"publisher","unstructured":"Berg T et al (2014) Birdsnap: Large-scale finegrained visual categorization of birds. In: 2014 IEEE conference on computer vision and pattern recognition, pp 2019\u20132026. https:\/\/doi.org\/10.1109\/CVPR.2014.259","DOI":"10.1109\/CVPR.2014.259"},{"key":"926_CR17","unstructured":"Boopathy A et al (2020) Proper network interpretability helps adversarial robustness in classification. In: International conference on machine learning. PMLR, pp 1014\u2013102"},{"key":"926_CR18","doi-asserted-by":"crossref","unstructured":"Bossard L, Guillaumin M, Gool LV (2014) Food-101 - mining discriminative components with random forests. In: ECCV","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"926_CR19","doi-asserted-by":"crossref","unstructured":"Breiman L (2001) Random forests. In: Machine learning, vol 45.1, pp 5\u201332","DOI":"10.1023\/A:1010933404324"},{"key":"926_CR20","unstructured":"Cantareira GD, Mello RF, Paulovich FV (2021) Explainable adversarial attacks in deep neural networks using activation profiles. In: arXiv:2103.10229"},{"key":"926_CR21","unstructured":"Codella N et al (2019) Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic). In: arXiv:1902.03368"},{"key":"926_CR22","unstructured":"CSE-CIC-IDS2018 on AWS. Accessed: 2022-03-25 (2018) https:\/\/www.unb.ca\/cic\/datasets\/ids-2018.html"},{"key":"926_CR23","doi-asserted-by":"crossref","unstructured":"Dellermann D et al (2019) Hybrid intelligence. In: Business & information systems engineering, vol 61.5, pp 637\u2013643","DOI":"10.1007\/s12599-019-00595-2"},{"key":"926_CR24","doi-asserted-by":"publisher","unstructured":"Deng J et al (2009) ImageNet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp 248\u2013255. https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"926_CR25","doi-asserted-by":"crossref","unstructured":"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\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"926_CR26","doi-asserted-by":"crossref","unstructured":"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\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"926_CR27","unstructured":"Dimanov B et al (2020) You Shouldn\u2019t Trust Me: Learning models which conceal unfairness from multiple explanation methods. In: SafeAI@AAAI"},{"key":"926_CR28","unstructured":"Dombrowski A-K et al (2019) Explanations can be manipulated and geometry is to blame. In: Advances in neural information processing systems, p 32"},{"key":"926_CR29","doi-asserted-by":"publisher","unstructured":"Do\u0161ilovi\u0107 FK, Br\u010dci\u0107 M, Hlupi\u0107 N (2018) Explainable artificial intelligence: A survey. In: 2018 41st International convention on information and communication technology, electronics and microelectronics (MIPRO), pp 0210\u20130215. https:\/\/doi.org\/10.23919\/MIPRO.2018.8400040","DOI":"10.23919\/MIPRO.2018.8400040"},{"key":"926_CR30","doi-asserted-by":"crossref","unstructured":"Van Eck D, McAdams DA, Vermaas PE (2007) Functional decomposition in engineering: a survey. In: International design engineering technical conferences and computers and information in engineering conference, vol 48043, pp 227\u2013236","DOI":"10.1115\/DETC2007-34232"},{"key":"926_CR31","unstructured":"Elson J et al (2007) Asirra: A CAPTCHA that exploits interest-aligned manual image categorization. In: CCS, vol 7, pp 366\u2013374"},{"key":"926_CR32","doi-asserted-by":"crossref","unstructured":"Fan Y et al (2021) Understanding update of machine-learning-based malware detection by clustering changes in feature attributions. In: International workshop on security. Springer, pp 99\u2013118","DOI":"10.1007\/978-3-030-85987-9_6"},{"key":"926_CR33","doi-asserted-by":"publisher","unstructured":"Faraway JJ (2016) Extending the linear model with R. Chapman and Hall\/CRC. https:\/\/doi.org\/10.1201\/9781315382722","DOI":"10.1201\/9781315382722"},{"key":"926_CR34","doi-asserted-by":"crossref","unstructured":"Farrugia D et al (2021) A real-time prescriptive solution for explainable Cyber-Fraud detection within the igaming industry. In: Sn computer science, p 2","DOI":"10.1007\/s42979-021-00623-7"},{"key":"926_CR35","doi-asserted-by":"crossref","unstructured":"Friedman JH (2001) Greedy function approximation: a gradient boosting machine. In: Annals of statistics, pp 1189\u20131232","DOI":"10.1214\/aos\/1013203451"},{"key":"926_CR36","doi-asserted-by":"crossref","unstructured":"Galkin F et al (2018) Human microbiome aging clocks based on deep learning and tandem of permutation feature importance and accumulated local effects. In: BioRxiv, p 507780","DOI":"10.1101\/507780"},{"key":"926_CR37","doi-asserted-by":"crossref","unstructured":"Galli A et al (2021) Reliability of explainable artificial intelligence in adversarial perturbation scenarios. In: International conference on pattern recognition. Springer, pp 243\u2013256","DOI":"10.1007\/978-3-030-68796-0_18"},{"key":"926_CR38","doi-asserted-by":"crossref","unstructured":"Ghorbani A, Abid A, Zou J (2019) Interpretation of neural networks is fragile. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 3681\u20133688","DOI":"10.1609\/aaai.v33i01.33013681"},{"key":"926_CR39","doi-asserted-by":"crossref","unstructured":"Giudici P, Raffinetti E (2022) Explainable AI methods in cyber risk management. In: Quality and reliability engineering international, vol 38.3, pp 1318\u20131326","DOI":"10.1002\/qre.2939"},{"key":"926_CR40","doi-asserted-by":"crossref","unstructured":"Giudici P, Raffinetti E (2021) Shapley-Lorenz eXplainable artificial intelligence. In: Expert systems with applications, vol 167, p 114104","DOI":"10.1016\/j.eswa.2020.114104"},{"key":"926_CR41","doi-asserted-by":"crossref","unstructured":"Goldstein A et al (2015) Peeking inside the black box: Visualizing statistical learning with plots of individual conditional expectation. In: Journal of computational and graphical statistics, vol 24.1, pp 44\u201365","DOI":"10.1080\/10618600.2014.907095"},{"key":"926_CR42","unstructured":"Goodfellow IJ, Shlens J, Szegedy C (2014) Explaining and harnessing adversarial examples. In: arXiv:1412.6572"},{"key":"926_CR43","doi-asserted-by":"crossref","unstructured":"Gulmezoglu B (2021) XAI-based microarchitectural side-channel analysis for website fingerprinting attacks and defenses. In: IEEE transactions on dependable and secure computing","DOI":"10.1109\/TDSC.2021.3117145"},{"key":"926_CR44","doi-asserted-by":"crossref","unstructured":"Gunning D, Aha D (2019) DARPA\u2019s explainable artificial intelligence (XAI) program. In: AI magazine, vol 40.2, pp 44\u201358","DOI":"10.1609\/aimag.v40i2.2850"},{"key":"926_CR45","doi-asserted-by":"crossref","unstructured":"Guo W et al (2018) Lemna: Explaining deep learning based security applications. In: proceedings of the 2018 ACM SIGSAC conference on computer and communications security, pp 364\u2013379","DOI":"10.1145\/3243734.3243792"},{"key":"926_CR46","doi-asserted-by":"publisher","unstructured":"Hagras H (2018) Toward Human-Understandable Explainable AI. In: Computer, vol 51.9, pp 28\u201336. https:\/\/doi.org\/10.1109\/MC.2018.3620965","DOI":"10.1109\/MC.2018.3620965"},{"key":"926_CR47","doi-asserted-by":"publisher","unstructured":"Hanif A, Zhang X, Wood S (2021) A survey on explainable artificial intelligence techniques and challenges. In: 2021 IEEE 25th international enterprise distributed object computing workshop (EDOCW), pp 81\u201389. https:\/\/doi.org\/10.1109\/EDOCW52865.2021.00036","DOI":"10.1109\/EDOCW52865.2021.00036"},{"key":"926_CR48","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The elements of statistical learning: data mining, inference, and prediction, vol 2","author":"T Hastie","year":"2009","unstructured":"Hastie T et al (2009) The elements of statistical learning: data mining, inference, and prediction, vol 2. Springer, Berlin"},{"key":"926_CR49","unstructured":"Heo J, Joo S, Moon T (2019) Fooling neural network interpretations via adversarial model manipulation. In: Advances in neural information processing systems, p 32"},{"key":"926_CR50","doi-asserted-by":"crossref","unstructured":"Holzinger A et al (2018) Current advances, trends and challenges of machine learning and knowledge extraction: from machine learning to explainable AI. In: International cross-domain conference for machine learning and knowledge extraction. Springer, pp 1\u20138","DOI":"10.1007\/978-3-319-99740-7_1"},{"key":"926_CR51","unstructured":"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\u2013606"},{"key":"926_CR52","unstructured":"Hooker S et al (2019) A benchmark for interpretability methods in deep neural networks. In: Advances in neural information processing systems, p 32"},{"key":"926_CR53","doi-asserted-by":"crossref","unstructured":"Iadarola G et al (2021) Towards an interpretable deep learning model for mobile malware detection and family identification. In: Computers & Security, vol 105, p 102198","DOI":"10.1016\/j.cose.2021.102198"},{"key":"926_CR54","unstructured":"Islam SR et al (2019) Domain knowledge aided explainable artificial intelligence for intrusion detection and response. In: arXiv:1911.09853"},{"key":"926_CR55","unstructured":"Kirchner L, Larson J, Mattu S, Angwin J (2020) Propublica Recidivism Dataset. https:\/\/www.propublica.org\/datastore\/dataset\/compas-recidivism-risk-score-data-and-analysis. Accessed 01 Aug\u00a02022"},{"key":"926_CR56","doi-asserted-by":"crossref","unstructured":"Kang H, Kim H et al (2021) Robust adversarial attack against explainable deep classification models based on adversarial images with different patch sizes and perturbation ratios. In: IEEE Access, vol 9, pp 133049\u2013133061","DOI":"10.1109\/ACCESS.2021.3115764"},{"key":"926_CR57","doi-asserted-by":"crossref","unstructured":"Karn RR et al (2020) Cryptomining detection in container clouds using system calls and explainable machine learning. In: IEEE transactions on parallel and distributed systems, vol 32.3, pp 674\u2013691","DOI":"10.1109\/TPDS.2020.3029088"},{"key":"926_CR58","doi-asserted-by":"crossref","unstructured":"Khan IA et al (2022) XSRU-IoMT: Explainable simple recurrent units for threat detection in Internet of Medical Things networks. In: Future generation computer systems, vol 127, pp 181\u2013193","DOI":"10.1016\/j.future.2021.09.010"},{"key":"926_CR59","doi-asserted-by":"crossref","unstructured":"Kindermans P-J et al (2019) The (un) reliability of saliency methods. In: Explainable AI: Interpreting, explaining and visualizing deep learning. Springer, pp 267\u2013280","DOI":"10.1007\/978-3-030-28954-6_14"},{"key":"926_CR60","doi-asserted-by":"crossref","unstructured":"Kingsford C, Salzberg SL (2008) What are decision trees?. In: Nature Biotechnology, vol 26.9, pp 1011\u20131013","DOI":"10.1038\/nbt0908-1011"},{"key":"926_CR61","volume-title":"Logistic regression","author":"DG Kleinbaum","year":"2002","unstructured":"Kleinbaum DG et al (2002) Logistic regression. Springer, New York"},{"key":"926_CR62","unstructured":"Kohavi R, Becker B (2020) UCI - Adult Dataset. https:\/\/archive.ics.uci.edu\/ml\/datasets\/adult"},{"key":"926_CR63","doi-asserted-by":"publisher","unstructured":"Koroniotis N et al (2019) Towards the development of realistic botnet dataset in the Internet of Things for network forensic analytics: Bot-IoT dataset. In: Future generation computer systems. issn: 0167-739X, vol 100, pp 779\u2013796. https:\/\/doi.org\/10.1016\/j.future.2019.05.041","DOI":"10.1016\/j.future.2019.05.041"},{"key":"926_CR64","unstructured":"Krizhevsky A, Hinton G et al (2009) Learning multiple layers of features from tiny images"},{"key":"926_CR65","doi-asserted-by":"crossref","unstructured":"Kuppa A, Le-Khac N-A (2021) Adversarial xai methods in cybersecurity. In: IEEE transactions on information forensics and security, vol 16, pp 4924\u20134938","DOI":"10.1109\/TIFS.2021.3117075"},{"key":"926_CR66","doi-asserted-by":"crossref","unstructured":"Kuppa A, Le-Khac N-A (2020) Black box attacks on explainable artificial intelligence (XAI) methods in cyber security. In: 2020 international joint conference on neural networks (IJCNN). IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN48605.2020.9206780"},{"key":"926_CR67","doi-asserted-by":"crossref","unstructured":"Kuppa A et al (2019) Finding rats in cats: Detecting stealthy attacks using group anomaly detection. In: 2019 18th IEEE international conference on trust, security and privacy in computing and communications\/13th IEEE international conference on big data science and engineering (TrustCom\/BigDataSE). IEEE, pp 442\u2013449","DOI":"10.1109\/TrustCom\/BigDataSE.2019.00066"},{"key":"926_CR68","doi-asserted-by":"crossref","unstructured":"Kurakin A, Goodfellow IJ, Bengio S (2018) Adversarial examples in the physical world. In: Artificial intelligence safety and security. Chapman and Hall\/CRC, pp 99\u2013112","DOI":"10.1201\/9781351251389-8"},{"key":"926_CR69","unstructured":"Ciontos A, Fenoy LM (2020) Performance evaluation of explainable ai methods against adversarial noise"},{"key":"926_CR70","doi-asserted-by":"crossref","unstructured":"La Malfa E et al (2021) On guaranteed optimal robust explanations for NLP models. In: arXiv:2105.03640","DOI":"10.24963\/ijcai.2021\/366"},{"key":"926_CR71","doi-asserted-by":"crossref","unstructured":"Lashkari AH et al (2017) Characterization of tor traffic using time based features. In: ICISSp, pp 253\u2013262","DOI":"10.5220\/0006105602530262"},{"key":"926_CR72","doi-asserted-by":"crossref","unstructured":"Le Merrer E, Tr\u00e9dan G (2020) Remote explainability faces the bouncer problem. In: Nature machine intelligence, vol 2.9, pp 529\u2013539","DOI":"10.1038\/s42256-020-0216-z"},{"key":"926_CR73","doi-asserted-by":"crossref","unstructured":"Li L-J, Fei-Fei L (2007) What, where and who? classifying events by scene and object recognition. In: 2007 IEEE 11th international conference on computer vision. IEEE, pp 1\u20138","DOI":"10.1109\/ICCV.2007.4408872"},{"key":"926_CR74","doi-asserted-by":"crossref","unstructured":"Lin Y-S, Lee W-C, Celik ZB (2020) What do you see? Evaluation of explainable artificial intelligence (XAI) interpretability through neural backdoors. In: arXiv:2009.10639","DOI":"10.1145\/3447548.3467213"},{"key":"926_CR75","doi-asserted-by":"crossref","unstructured":"Liu B et al (2021) When machine learning meets privacy: A survey and outlook. In: ACM Computing Surveys (CSUR), vol 54.2, pp 1\u201336","DOI":"10.1145\/3436755"},{"key":"926_CR76","doi-asserted-by":"crossref","unstructured":"Liu H et al (2021) FAIXID: a framework for enhancing ai explainability of intrusion detection results using data cleaning techniques. In: Journal of network and systems management, vol 29.4, pp 1\u201330","DOI":"10.1007\/s10922-021-09606-8"},{"key":"926_CR77","doi-asserted-by":"crossref","unstructured":"Longo L et al (2020) Explainable artificial intelligence: Concepts, applications, research challenges and visions. In: International cross-domain conference for machine learning and knowledge extraction. Springer, pp 1\u201316","DOI":"10.1007\/978-3-030-57321-8_1"},{"key":"926_CR78","unstructured":"Lundberg SM, Lee S-I (2017) A unified approach to interpreting model predictions. In: Advances in neural information processing systems, p 30"},{"key":"926_CR79","doi-asserted-by":"crossref","unstructured":"Mahbooba B et al (2021) Explainable artificial intelligence (xai) to enhance trust management in intrusion detection systems using decision tree model. In: Complexity, 2021","DOI":"10.1155\/2021\/6634811"},{"key":"926_CR80","doi-asserted-by":"crossref","unstructured":"Mahdavifar S, Alhadidi D, Ghorbani A et al (2022) Effective and efficient hybrid android malware classification using pseudo-label stacked auto-encoder. In: Journal of network and systems management, vol 30.1, pp 1\u201334","DOI":"10.1007\/s10922-021-09634-4"},{"key":"926_CR81","doi-asserted-by":"crossref","unstructured":"Mamun MSI et al (2016) Detecting malicious urls using lexical analysis. In: International conference on network and system security. Springer, pp 467\u2013482","DOI":"10.1007\/978-3-319-46298-1_30"},{"key":"926_CR82","doi-asserted-by":"crossref","unstructured":"Marino DL, Wickramasinghe CS, Manic M (2018) An adversarial approach for explainable ai in intrusion detection systems. In: IECON 2018-44th annual conference of the IEEE industrial electronics society. IEEE, pp 3237\u20133243","DOI":"10.1109\/IECON.2018.8591457"},{"key":"926_CR83","doi-asserted-by":"crossref","unstructured":"Melis M et al (2022) Do gradient-based explanations tell anything about adversarial robustness to android malware?. In: International journal of machine learning and cybernetics, vol 13.1, pp 217\u2013232","DOI":"10.1007\/s13042-021-01393-7"},{"key":"926_CR84","unstructured":"Miura T, Hasegawa S, Shibahara T (2021) MEGEX: Data-free model extraction attack against gradient-based explainable AI. In: arXiv:2107.08909"},{"key":"926_CR85","unstructured":"Molnar C (2018) A guide for making black box models explainable. In:\u00a0https:\/\/christophm.github.io\/interpretable-ml-book. Accessed 01 Aug 2022"},{"key":"926_CR86","doi-asserted-by":"crossref","unstructured":"MontazeriShatoori M et al (2020) Detection of doh tunnels using time-series classification of encrypted traffic. In: 2020 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). IEEE, pp 63\u201370","DOI":"10.1109\/DASC-PICom-CBDCom-CyberSciTech49142.2020.00026"},{"key":"926_CR87","unstructured":"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\u201325"},{"key":"926_CR88","doi-asserted-by":"crossref","unstructured":"Moustafa N, Slay J (2015) UNSW-NB15: a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set). In: 2015 military communications and information systems conference (MilCIS). IEEE, pp 1\u20136","DOI":"10.1109\/MilCIS.2015.7348942"},{"key":"926_CR89","doi-asserted-by":"crossref","unstructured":"Muddamsetty SM et al (2022) Visual explanation of black-box model: Similarity difference and uniqueness (SIDU) method. In: Pattern recognition, vol 127, p 108604","DOI":"10.1016\/j.patcog.2022.108604"},{"key":"926_CR90","doi-asserted-by":"crossref","unstructured":"M\u00fcller J, Shoemaker CA, Pich\u00e9 R (2013) SO-MI: A surrogate model algorithm for computationally expensive nonlinear mixed-integer black-box global optimization problems. In: Computers & operations research, vol 40.5, pp 1383\u20131400","DOI":"10.1016\/j.cor.2012.08.022"},{"key":"926_CR91","unstructured":"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"},{"key":"926_CR92","doi-asserted-by":"crossref","unstructured":"Nguyen A, Yosinski J, Clune J (2019) Understanding neural networks via feature visualization: A survey. In: Explainable AI: interpreting, explaining and visualizing deep learning. Springer, pp 55\u201376","DOI":"10.1007\/978-3-030-28954-6_4"},{"key":"926_CR93","doi-asserted-by":"crossref","unstructured":"Pag\u00e8s J (2014) Multiple factor analysis by example using R. CRC Press","DOI":"10.1201\/b17700"},{"key":"926_CR94","unstructured":"Paredes J et al (2021) On the importance of domainspecific explanations in AI-based cybersecurity systems (Technical Report). In: arXiv:2108.02006"},{"key":"926_CR95","doi-asserted-by":"crossref","unstructured":"Pedreshi D, Ruggieri S, Turini F (2008) Discrimination-aware data mining. In: Proceedings of the 14th ACM SIGKDD international conference on knowledge discovery and data mining, pp 560\u2013568","DOI":"10.1145\/1401890.1401959"},{"key":"926_CR96","doi-asserted-by":"publisher","unstructured":"Pierazzi F et al (2020) Intriguing properties of adversarial ML Attacks in the problem space. English. In: 2020 IEEE symposium on security and privacy. issn: 2375\u20131207, pp 1332\u20131349. https:\/\/doi.org\/10.1109\/SP40000.2020.00073","DOI":"10.1109\/SP40000.2020.00073"},{"key":"926_CR97","doi-asserted-by":"crossref","unstructured":"Ribeiro MT, Singh S, Guestrin C (2016) Why should i trust you? Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 1135\u20131144","DOI":"10.1145\/2939672.2939778"},{"key":"926_CR98","doi-asserted-by":"crossref","unstructured":"Ribeiro MT, Singh S, Guestrin C (2018) Anchors: High-precision modelagnostic explanations. In: Proceedings of the AAAI conference on artificial intelligence, vol 32, p 1","DOI":"10.1609\/aaai.v32i1.11491"},{"key":"926_CR99","unstructured":"Rieger L, Hansen LK (2020) A simple defense against adversarial attacks on heatmap explanations. In: arXiv:2007.06381"},{"key":"926_CR100","unstructured":"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\u201346"},{"key":"926_CR101","doi-asserted-by":"crossref","unstructured":"Rosenblatt F (1958) The Perceptron: A probabilistic model for information storage and organization in the brain. In: Psychological review, pp 65\u2013386","DOI":"10.1037\/h0042519"},{"key":"926_CR102","doi-asserted-by":"crossref","unstructured":"Roshan K, Zafar A (2021) Utilizing XAI technique to improve autoencoder based model for computer network anomaly detection with shapley additive explanation(SHAP). In: arXiv:2112.08442","DOI":"10.5121\/ijcnc.2021.13607"},{"key":"926_CR103","doi-asserted-by":"crossref","unstructured":"Russakovsky O et al (2015) Imagenet large scale visual recognition challenge. In: International journal of computer vision, vol 115.3, pp 211\u2013252","DOI":"10.1007\/s11263-015-0816-y"},{"key":"926_CR104","unstructured":"Samek W, Wiegand T, M\u00fcller K-R (2017) Explainable artificial intelligence: Understanding, visualizing and interpreting deep learning models. In: arXiv:1708.08296"},{"key":"926_CR105","doi-asserted-by":"crossref","unstructured":"Samek W et al (2021) Explaining deep neural networks and beyond: A review of methods and applications. In: Proceedings of the IEEE, vol 109.3, pp 247\u2013278","DOI":"10.1109\/JPROC.2021.3060483"},{"key":"926_CR106","doi-asserted-by":"crossref","unstructured":"Sarhan M, Layeghy S, Portmann M (2021) Evaluating standard feature sets towards increased generalisability and explainability of ML-based network intrusion detection","DOI":"10.1016\/j.bdr.2022.100359"},{"key":"926_CR107","doi-asserted-by":"crossref","unstructured":"Sarhan M, Layeghy S, Portmann M (2021) Towards a standard feature set for network intrusion detection system datasets. In: Mobile networks and applications, pp 1\u201314","DOI":"10.1007\/s11036-021-01843-0"},{"key":"926_CR108","doi-asserted-by":"crossref","unstructured":"Selvaraju RR et al (2017) Grad-cam: Visual explanations from deep networks via gradientbased localization. In: Proceedings of the IEEE international conference on computer vision, pp 618\u2013626","DOI":"10.1109\/ICCV.2017.74"},{"key":"926_CR109","doi-asserted-by":"crossref","unstructured":"Shahid MR, Debar H (2021) CVSSBERT: Explainable natural language processing to determine the severity of a computer security vulnerability from its description. In: 2021 20th IEEE international conference on machine learning and applications (ICMLA). IEEE, pp 1600\u20131607","DOI":"10.1109\/ICMLA52953.2021.00256"},{"key":"926_CR110","doi-asserted-by":"crossref","unstructured":"Sharafaldin I, Lashkari AH, Ghorbani AA (2018) Toward generating a new intrusion detection dataset and intrusion traffic characterization. In: ICISSp, vol 1, pp 108\u2013116","DOI":"10.5220\/0006639801080116"},{"key":"926_CR111","doi-asserted-by":"crossref","unstructured":"Shaukat K et al (2020) A survey on machine learning techniques for cyber security in the last decade. In: IEEE Access, vol 8, pp 222310\u2013222354","DOI":"10.1109\/ACCESS.2020.3041951"},{"key":"926_CR112","doi-asserted-by":"crossref","unstructured":"Shi Y et al (2020) Adaptive iterative attack towards explainable adversarial robustness. In: Pattern recognition, vol 105, p 107309","DOI":"10.1016\/j.patcog.2020.107309"},{"key":"926_CR113","doi-asserted-by":"crossref","unstructured":"Shokri R, Strobel M, Zick Y (2021) On the privacy risks of model explanations. In: Proceedings of the 2021 AAAI\/ACM Conference on AI, Ethics, and Society, pp 231\u2013241","DOI":"10.1145\/3461702.3462533"},{"key":"926_CR114","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. In: arXiv:1409.1556"},{"key":"926_CR115","doi-asserted-by":"crossref","unstructured":"Sinha S et al (2021) Perturbing inputs for fragile interpretations in deep natural language processing. In: arXiv:2108.04990","DOI":"10.18653\/v1\/2021.blackboxnlp-1.33"},{"key":"926_CR116","unstructured":"Slack DZ et al (2021) Reliable Post hoc Explanations: Modeling Uncertainty in Explainability. In: Beygelzimer A et al (eds) Advances in neural information processing systems.\u00a0https:\/\/openreview.net\/forum?id=rqfq0CYIekd. Accessed 01 Aug 2022"},{"key":"926_CR117","unstructured":"Slack D et al (2021) Counterfactual explanations can be manipulated. In: Advances in neural information processing systems, vol 34, pp 62\u201375"},{"key":"926_CR118","doi-asserted-by":"crossref","unstructured":"Slack D et al (2020) Fooling lime and shap: Adversarial attacks on post hoc explanation methods. In: Proceedings of the AAAI\/ACM conference on AI, Ethics, and Society, pp 180\u2013186","DOI":"10.1145\/3375627.3375830"},{"key":"926_CR119","unstructured":"Smilkov D et al (2017) SmoothGrad: removing noise by adding noise. In: arXiv:1706.03825"},{"key":"926_CR120","doi-asserted-by":"crossref","unstructured":"Smutz C, Stavrou A (2012) Malicious PDF detection using metadata and structural features. In: Proceedings of the 28th annual computer security applications conference, pp 239\u2013248","DOI":"10.1145\/2420950.2420987"},{"key":"926_CR121","unstructured":"Srivastava G et al (2022) XAI for Cybersecurity: State of the Art, Challenges, Open Issues and Future Directions. In: arXiv:2206.03585"},{"key":"926_CR122","unstructured":"Sundararajan M, Taly A, Yan Q (2017) Axiomatic attribution for deep networks. In: International conference on machine learning. PMLR, pp 3319\u20133328"},{"key":"926_CR123","doi-asserted-by":"crossref","unstructured":"Szczepa\u0144ski M et al (2020) Achieving explainability of intrusion detection system by hybrid oracle-explainer approach. In: 2020 international joint conference on neural networks (IJCNN). IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN48605.2020.9207199"},{"key":"926_CR124","unstructured":"Tahmina Z, Rezvy S, Yuan L et al (2022) An explainable ai-based intrusion detection system for DNS over HTTPS (DoH) Attacks. In: Techrxiv"},{"key":"926_CR125","doi-asserted-by":"crossref","unstructured":"Takahashi T et al (2021) Designing comprehensive cyber threat analysis platform: Can we orchestrate analysis engines?. In: 2021 IEEE international conference on pervasive computing and communications workshops and other affiliated events (PerCom Workshops). IEEE, pp 376\u2013379","DOI":"10.1109\/PerComWorkshops51409.2021.9431125"},{"key":"926_CR126","doi-asserted-by":"crossref","unstructured":"Tavallaee M et al (2009) A detailed analysis of the KDD CUP 99 data set. In: 2009 IEEE symposium on computational intelligence for security and defense applications. Ieee, pp 1\u20136","DOI":"10.1109\/CISDA.2009.5356528"},{"key":"926_CR127","doi-asserted-by":"crossref","unstructured":"Truong J-B et al (2021) Data-free model extraction. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4771\u20134780","DOI":"10.1109\/CVPR46437.2021.00474"},{"key":"926_CR128","doi-asserted-by":"crossref","unstructured":"Vigano L, Magazzeni D (2020) Explainable security. In: 2020 IEEE European symposium on security and privacy workshops (EuroS&PW). IEEE, pp 293\u2013300","DOI":"10.1109\/EuroSPW51379.2020.00045"},{"key":"926_CR129","unstructured":"Virus Share: Virus Report Sharing. Accessed: 2022-03-22. https:\/\/virusshare.com"},{"key":"926_CR130","doi-asserted-by":"crossref","unstructured":"Wachter S, Mittelstadt B, Russell C (2017) Counterfactual explanations without opening the black box: Automated decisions and the GDPR. In: Harv. JL & Tech, vol 31, p 841","DOI":"10.2139\/ssrn.3063289"},{"key":"926_CR131","doi-asserted-by":"publisher","unstructured":"Wali S, Khan I (2021) Explainable AI and random forest based reliable intrusion detection system. In: https:\/\/doi.org\/10.36227\/techrxiv.17169080.v1","DOI":"10.36227\/techrxiv.17169080.v1"},{"key":"926_CR132","doi-asserted-by":"crossref","unstructured":"Wang M et al (2020) An explainable machine learning framework for intrusion detection systems. In: IEEE Access, vol 8, pp 73127\u201373141","DOI":"10.1109\/ACCESS.2020.2988359"},{"key":"926_CR133","unstructured":"Wang S et al (2016) Trafficav: An effective and explainable detection of mobile malware behavior using network traffic. In: 2016 IEEE\/ACM 24th international symposium on quality of service (IWQoS). IEEE, pp 1\u20136"},{"key":"926_CR134","unstructured":"Wang Z et al (2020) Smoothed geometry for robust attribution. In: Advances in neural information processing systems, vol 33, pp 13623\u201313634"},{"key":"926_CR135","doi-asserted-by":"crossref","unstructured":"Xu F et al (2019) Explainable AI: A brief survey on history, research areas, approaches and challenges. In: CCF international conference on natural language processing and Chinese computing. Springer, pp. 563\u2013574","DOI":"10.1007\/978-3-030-32236-6_51"},{"key":"926_CR136","doi-asserted-by":"publisher","unstructured":"Zeng X, Martinez T (2001) Distribution-balanced stratified cross-validation for accuracy estimation. In: Journal of experimental & theoretical artificial intelligence vol 12. https:\/\/doi.org\/10.1080\/095281300146272","DOI":"10.1080\/095281300146272"},{"key":"926_CR137","doi-asserted-by":"crossref","unstructured":"Zeng Z et al (2015) A novel feature selection method considering feature interaction. In: Pattern recognition, vol 48.8, pp 2656\u20132666","DOI":"10.1016\/j.patcog.2015.02.025"},{"key":"926_CR138","doi-asserted-by":"crossref","unstructured":"Zhang Q et al (2018) Interpreting cnn knowledge via an explanatory graph. In: Proceedings of the AAAI conference on artificial intelligence, vol 32, p 1","DOI":"10.1609\/aaai.v32i1.11819"},{"key":"926_CR139","unstructured":"Zhang X et al (2020) Interpretable deep learning under fire. In: 29th fUSENIXg Security Symposium (fUSENIXg Security 20)"},{"key":"926_CR140","unstructured":"Zhao X et al (2021) BayLIME: Bayesian local interpretable model-agnostic explanations. In: UAI"},{"key":"926_CR141","doi-asserted-by":"crossref","unstructured":"Zhao X et al (2021) Exploiting explanations for model inversion attacks. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 682\u2013692","DOI":"10.1109\/ICCV48922.2021.00072"},{"key":"926_CR142","doi-asserted-by":"crossref","unstructured":"Zolanvari M et al (2019) Machine learning-based network vulnerability analysis of industrial Internet of Things. In: IEEE internet of things journal, vol 6.4, pp 6822\u20136834","DOI":"10.1109\/JIOT.2019.2912022"},{"key":"926_CR143","doi-asserted-by":"crossref","unstructured":"Zolanvari M et al (2021) TRUST XAI: Model-agnostic explanations for AI With a Case Study on IIoT Security. In: IEEE internet of things journal","DOI":"10.1109\/JIOT.2021.3122019"}],"container-title":["Annals of Telecommunications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12243-022-00926-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12243-022-00926-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12243-022-00926-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T03:16:13Z","timestamp":1670296573000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12243-022-00926-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,26]]},"references-count":143,"journal-issue":{"issue":"11-12","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["926"],"URL":"https:\/\/doi.org\/10.1007\/s12243-022-00926-7","relation":{},"ISSN":["0003-4347","1958-9395"],"issn-type":[{"value":"0003-4347","type":"print"},{"value":"1958-9395","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,26]]},"assertion":[{"value":"30 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 August 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 October 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}