{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T19:16:31Z","timestamp":1780427791865,"version":"3.54.1"},"reference-count":66,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T00:00:00Z","timestamp":1710892800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T00:00:00Z","timestamp":1710892800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Intelligent Data Analysis: An International Journal"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>\n                    The quest for transparency in black-box models has gained significant momentum in recent years. In particular, discovering the underlying machine learning technique type (or model family) from the performance of a black-box model is a real important problem both for better understanding its behaviour and for developing strategies to\n                    <jats:italic toggle=\"yes\">attack<\/jats:italic>\n                    it by exploiting the weaknesses intrinsic to the learning technique. In this paper, we tackle the challenging task of identifying which\n                    <jats:italic toggle=\"yes\">kind<\/jats:italic>\n                    of machine learning model is behind the predictions when we interact with a black-box model. Our innovative method involves systematically querying a black-box model (oracle) to label an artificially generated dataset, which is then used to train different surrogate models using machine learning techniques from different families (each one trying to partially approximate the oracle\u2019s behaviour). We present two approaches based on similarity measures, one selecting the most similar family and the other using a conveniently constructed meta-model. In both cases, we use both crisp and soft classifiers and their corresponding similarity metrics. By experimentally comparing all these methods, we gain valuable insights into the explanatory and predictive capabilities of our model family concept. This provides a deeper understanding of the black-box models and increases their transparency and interpretability, paving the way for more effective decision making.\n                  <\/jats:p>","DOI":"10.3233\/ida-230707","type":"journal-article","created":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T13:56:55Z","timestamp":1714139815000},"page":"28-44","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":5,"title":["Cracking black-box models: Revealing hidden machine learning techniques behind their predictions"],"prefix":"10.1177","volume":"29","author":[{"given":"Ra\u00fcl","family":"Fabra-Boluda","sequence":"first","affiliation":[{"name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","place":["Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C\u00e8sar","family":"Ferri","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","place":["Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jos\u00e9","family":"Hern\u00e1ndez-Orallo","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","place":["Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M. Jos\u00e9","family":"Ramrez-Quintana","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","place":["Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fernando","family":"Martnez-Plumed","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","place":["Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2024,3,20]]},"reference":[{"key":"e_1_3_2_2_2","first-page":"175","article-title":"Modelling Machine Learning Models","author":"Fabra-Boluda R.","year":"2017","unstructured":"Fabra-Boluda R., Ferri C., Hern\u00e1ndez-Orallo J., Mart\u00ednez-Plumed F., Ram\u00edrez-Quintana M.J., Modelling Machine Learning Models, in: 3rd Conf. on\u201d Philosophy and Theory of Artificial Intelligence, Springer, (2017), 175\u2013186.","journal-title":"3rd Conf. on\u201d Philosophy and Theory of Artificial Intelligence"},{"key":"e_1_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Joseph A.D. Nelson B. Rubinstein B.I. Tygar J. Adversarial machine learning Cambridge University Press (2018).","DOI":"10.1017\/9781107338548"},{"key":"e_1_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Vorobeychik Y. Kantarcioglu M. Brachman R. Stone P. Rossi F. Adversarial machine learning 12 Springer (2018).","DOI":"10.1007\/978-3-031-01580-9"},{"key":"e_1_3_2_5_2","unstructured":"Molnar C. et\u00a0al Interpretable machine learning: A guide for making black box models explainable Christoph Molnar Leanpub (2018)."},{"key":"e_1_3_2_6_2","first-page":"1","article-title":"Interpreting black-box models: a review on explainable artificial intelligence","author":"Hassija V.","year":"2023","unstructured":"Hassija V., Chamola V., Mahapatra A., Singal A., Goel D., Huang K., Scardapane S., Spinelli I., Mahmud M., Hussain A., Interpreting black-box models: a review on explainable artificial intelligence, Cognitive Computation (2023), 1\u201330.","journal-title":"Cognitive Computation"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-02300-7_4"},{"key":"e_1_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Wang Y. Sun T. Li S. Yuan X. Ni W. Hossain E. Poor H.V. Adversarial attacks and defenses in machine learning-powered networks: a contemporary survey arXiv preprint arXiv:2303.06302. (2023).","DOI":"10.1109\/COMST.2023.3319492"},{"key":"e_1_3_2_9_2","first-page":"43","article-title":"Adversarial machine learning","author":"Huang L.","year":"2011","unstructured":"Huang L., Joseph A.D., Nelson B., Rubinstein B.I., Tygar J., Adversarial machine learning, in: Proc. of the 4th ACM WS. on Security and artificial intelligence, (2011), 43\u201358.","journal-title":"Proc. of the 4th ACM WS. on Security and artificial intelligence"},{"key":"e_1_3_2_10_2","first-page":"601","article-title":"Stealing machine learning models via prediction APIs.","author":"Tram\u00e8r F.","year":"2016","unstructured":"Tram\u00e8r F., Zhang F., Juels A., Reiter M.K., Ristenpart T., Stealing machine learning models via prediction APIs., in: USENIX Security Symp., (2016), 601\u2013618.","journal-title":"USENIX Security Symp."},{"key":"e_1_3_2_11_2","unstructured":"Papernot N. McDaniel P. Goodfellow I. Transferability in machine learning: from phenomena to black-box attacks using adversarial samples arXiv preprint arXiv:1605.07277. (2016)."},{"key":"e_1_3_2_12_2","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","volume":"31","author":"Lee K.","year":"2018","unstructured":"Lee K., Lee K., Shin J., A simple unified framework for detecting out-of-distribution samples and adversarial attacks, Advances in Neural Information Processing Systems 31 (2018).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2981604"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190706"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3381028"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3083060"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0088-2"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1115255"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2020.0099"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2014.02.008"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.3390\/app10010046"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1177\/0261927X09351676"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.102141"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/293347.293351"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/1968.1972"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/0890-5401(87)90052-6"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022821128753"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/0304-3975(91)90026-X"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472291"},{"key":"e_1_3_2_30_2","first-page":"1","article-title":"From theories to queries: Active learning in practice","author":"Settles B.","year":"2011","unstructured":"Settles B., From theories to queries: Active learning in practice, in: Active Learning and Experimental Design WS. in conjunction with AISTATS 2010, (2011), 1\u201318.","journal-title":"Active Learning and Experimental Design WS. in conjunction with AISTATS 2010"},{"key":"e_1_3_2_31_2","unstructured":"Wiyatno R.R. Xu A. Dia O. De\u00a0Berker A. Adversarial Examples in Modern Machine Learning: A Review arXiv preprint arXiv:1911.05268. (2019)."},{"key":"e_1_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Tabassi E. Burns K.J. Hadjimichael M. Molina-Markham A.D. Sexton J.T. A taxonomy and terminology of adversarial machine learning NIST IR2019 (2019) 1\u201329.","DOI":"10.6028\/NIST.IR.8269-draft"},{"key":"e_1_3_2_33_2","unstructured":"Li G. Zhu P. Li J. Yang Z. Cao N. Chen Z. Security matters: A survey on adversarial machine learning arXiv preprint arXiv:1810.07339. (2018)."},{"key":"e_1_3_2_34_2","doi-asserted-by":"crossref","unstructured":"Biggio B. Roli F. Wild patterns: Ten years after the rise of adversarial machine learning in: Proc. of the 2018 ACM SIGSAC Conf. on Computer and Communications Security (2018) 2154\u20132156.","DOI":"10.1145\/3243734.3264418"},{"key":"e_1_3_2_35_2","first-page":"2137","article-title":"Black-box adversarial attacks with limited queries and information","author":"Ilyas A.","year":"2018","unstructured":"Ilyas A., Engstrom L., Athalye A., Lin J., Black-box adversarial attacks with limited queries and information, in: International Conf. on Machine Learning, PMLR, (2018), 2137\u20132146.","journal-title":"International Conf. on Machine Learning"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"e_1_3_2_38_2","first-page":"506","article-title":"Practical black-box attacks against machine learning","author":"Papernot N.","year":"2017","unstructured":"Papernot N., McDaniel P., Goodfellow I., Jha S., Celik Z.B., Swami A., Practical black-box attacks against machine learning, in: Proc. of the 2017 ACM on Asia Conf. on Computer And Communications Security, (2017), 506\u2013519.","journal-title":"Proc. of the 2017 ACM on Asia Conf. on Computer And Communications Security"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2886017"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-1998-2303"},{"key":"e_1_3_2_41_2","first-page":"35","article-title":"Analysing the trade-off between comprehensibility and accuracy in mimetic models","author":"Blanco-Vega R.","year":"2004","unstructured":"Blanco-Vega R., Hern\u00e1ndez-Orallo J., Ram\u00edrez-Quintana M., Analysing the trade-off between comprehensibility and accuracy in mimetic models, in: Discovery Science, (2004), 35\u201339.","journal-title":"Discovery Science"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/11.2.185"},{"key":"e_1_3_2_43_2","first-page":"12288","article-title":"Learning black-box attackers with transferable priors and query feedback","volume":"33","author":"Yang J.","year":"2020","unstructured":"Yang J., Jiang Y., Huang X., Ni B., Zhao C., Learning black-box attackers with transferable priors and query feedback, Advances in Neural Information Processing Systems 33 (2020), 12288\u201312299.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aay7120"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_2_46_2","unstructured":"Guidotti R. Monreale A. Ruggieri S. Pedreschi D. Turini F. Giannotti F. Local rule-based explanations of black box decision systems arXiv preprint arXiv:1805.10820. (2018)."},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12102215"},{"key":"e_1_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Oh S.J. Schiele B. Fritz M. Towards reverse-engineering black-box neural networks Explainable AI: Interpreting Explaining and Visualizing Deep Learning (2019) 121\u2013144.","DOI":"10.1007\/978-3-030-28954-6_7"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1117\/1.OE.51.11.111707"},{"key":"e_1_3_2_50_2","article-title":"An application of hierarchical kappa-type statistics in the assessment of majority agreement among multiple observers","author":"Landis J.R.","unstructured":"Landis J.R., Koch G.G., An application of hierarchical kappa-type statistics in the assessment of majority agreement among multiple observers, Biometrics (1977), 363\u2013374.","journal-title":"Biometrics"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.08.010"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80023-1"},{"key":"e_1_3_2_53_2","unstructured":"R Core Team R: A Language and Environment for Statistical Computing R Foundation for Statistical Computing Vienna Austria (2019. http:\/\/www.R-project.org\/."},{"issue":"5","key":"e_1_3_2_54_2","first-page":"1","article-title":"Building Predictive Models in R Using the caret Package","volume":"28","author":"Kuhn M.","year":"2008","unstructured":"Kuhn M., Building Predictive Models in R Using the caret Package, Journal of Statistical Software, Articles 28(5) (2008), 1\u201326. doi: https:\/\/doi.org\/10.18637\/jss.v028.i05. https:\/\/www.jstatsoft.org\/v028\/i05.","journal-title":"Journal of Statistical Software, Articles"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-17711-8_5"},{"issue":"1","key":"e_1_3_2_56_2","first-page":"3133","article-title":"Do we need hundreds of classifiers to solve real world classification problems","volume":"15","author":"Fern\u00e1ndez-Delgado M.","year":"2014","unstructured":"Fern\u00e1ndez-Delgado M., Cernadas E., Barro S., Amorim D., Do we need hundreds of classifiers to solve real world classification problems, J Mach Learn Res 15(1) (2014), 3133\u20133181.","journal-title":"J Mach Learn Res"},{"key":"e_1_3_2_57_2","first-page":"1140","article-title":"Making sense of item response theory in machine learning","volume":"285","author":"Mart\u0131nez-Plumed F.","year":"2016","unstructured":"Mart\u0131nez-Plumed F., Prud\u00eancio R.B., Mart\u0131nez-Us\u00f3 A., Hern\u00e1ndez-Orallo J., Making sense of item response theory in machine learning, in: Proc. of 22nd European Conf. on Artificial Intelligence (ECAI), Frontiers in Artificial Intelligence and Applications 285 (2016), 1140\u20131148.","journal-title":"Proc. of 22nd European Conf. on Artificial Intelligence (ECAI), Frontiers in Artificial Intelligence and Applications"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5422-z"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/2641190.2641198"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_3_2_61_2","first-page":"99","article-title":"On a measure of divergence between two statistical populations defined by their probability distribution","volume":"35","author":"Bhattacharyya A.","year":"1943","unstructured":"Bhattacharyya A., On a measure of divergence between two statistical populations defined by their probability distribution, Bulletin of the Calcutta Mathematical Society 35 (1943), 99\u2013110.","journal-title":"Bulletin of the Calcutta Mathematical Society"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-8137.1912.tb05611.x"},{"key":"e_1_3_2_63_2","unstructured":"Tanimoto T.T. Elementary mathematical theory of classification and prediction (1958)."},{"issue":"2","key":"e_1_3_2_64_2","first-page":"1","article-title":"Comprehensive survey on distance\/similarity measures between probability density functions","volume":"1","author":"Cha S.-H.","year":"2007","unstructured":"Cha S.-H., Comprehensive survey on distance\/similarity measures between probability density functions, City 1(2) (2007), 1.","journal-title":"City"},{"issue":"2","key":"e_1_3_2_65_2","first-page":"239","article-title":"Comparison of three methods for selecting values of input variables in the analysis of output from a computer code","volume":"21","author":"McKay M.D.","year":"1979","unstructured":"McKay M.D., Beckman R.J., Conover W.J., Comparison of three methods for selecting values of input variables in the analysis of output from a computer code, Technometrics 21(2) (1979), 239\u2013245.","journal-title":"Technometrics"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.4208\/nmtma.2010.32s.1"},{"issue":"4","key":"e_1_3_2_67_2","first-page":"784","article-title":"On the distribution of points in a cube and the approximate evaluation of integrals","volume":"7","author":"Sobol\u2019 I.M.","year":"1967","unstructured":"Sobol\u2019 I.M., On the distribution of points in a cube and the approximate evaluation of integrals, Zhurnal Vychislitel\u2019noi Matematiki i Matematicheskoi Fiziki 7(4) (1967), 784\u2013802.","journal-title":"Zhurnal Vychislitel\u2019noi Matematiki i Matematicheskoi Fiziki"}],"container-title":["Intelligent Data Analysis: An International Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/IDA-230707","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/IDA-230707","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/IDA-230707","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:20:47Z","timestamp":1777454447000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/IDA-230707"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,20]]},"references-count":66,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.3233\/IDA-230707"],"URL":"https:\/\/doi.org\/10.3233\/ida-230707","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,20]]}}}