{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:47:10Z","timestamp":1767340030834,"version":"3.40.5"},"reference-count":55,"publisher":"SAGE Publications","issue":"7","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Distributed Sensor Networks"],"published-print":{"date-parts":[[2022,7]]},"abstract":"<jats:p> Despite the encouraging outcomes of machine learning and artificial intelligence applications, the safety of artificial intelligence\u2013based systems is one of the most severe challenges that need further exploration. Data set poisoning is a severe problem that may lead to the corruption of machine learning models. The attacker injects data into the data set that are faulty or mislabeled by flipping the actual labels into the incorrect ones. The word \u201crobustness\u201d refers to a machine learning algorithm\u2019s ability to cope with hostile situations. Here, instead of flipping the labels randomly, we use the clustering approach to choose the training samples for label changes to influence the classifiers\u2019 performance and the distance-based anomaly detection capacity in quarantining the poisoned samples. According to our experiments on a benchmark data set, random label flipping may have a short-term negative impact on the classifier\u2019s accuracy. Yet, an anomaly filter would discover on average 63% of them. On the contrary, the proposed clustering-based flipping might inject dormant poisoned samples until the number of poisoned samples is enough to influence the classifiers\u2019 performance severely; on average, the same anomaly filter would discover 25% of them. We also highlight important lessons and observations during this experiment about the performance and robustness of popular multiclass learners against training data set\u2013poisoning attacks that include: trade-offs, complexity, categories, poisoning resistance, and hyperparameter optimization. <\/jats:p>","DOI":"10.1177\/15501329221105159","type":"journal-article","created":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T10:38:24Z","timestamp":1657795104000},"page":"155013292211051","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":7,"title":["The robustness of popular multiclass machine learning models against poisoning attacks: Lessons and insights"],"prefix":"10.1177","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4822-417X","authenticated-orcid":false,"given":"Majdi","family":"Maabreh","sequence":"first","affiliation":[{"name":"Department of Information Technology, Faculty of Prince Al-Hussein Bin Abdallah II for Information Technology, The Hashemite University, Zarqa, Jordan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arwa","family":"Maabreh","sequence":"additional","affiliation":[{"name":"Department of Statistics, Faculty of Science, Yarmouk University, Irbid, Jordan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Basheer","family":"Qolomany","sequence":"additional","affiliation":[{"name":"Cyber Systems Department, The University of Nebraska at Kearney, Kearney, NE, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ala","family":"Al-Fuqaha","sequence":"additional","affiliation":[{"name":"Division of Information & Computing Technology (ICT), College of Science & Engineering (CSE), Hamad Bin Khalifa University, Doha, Qatar"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2022,7,14]]},"reference":[{"key":"bibr1-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2021.02.006"},{"key":"bibr2-15501329221105159","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph18010271"},{"key":"bibr3-15501329221105159","doi-asserted-by":"publisher","DOI":"10.4018\/JCIT.2021010101"},{"key":"bibr4-15501329221105159","doi-asserted-by":"publisher","DOI":"10.3390\/su13010351"},{"key":"bibr5-15501329221105159","doi-asserted-by":"publisher","DOI":"10.3390\/smartcities4020040"},{"key":"bibr6-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.113074"},{"key":"bibr7-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtte.2020.07.004"},{"key":"bibr8-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2020.100345"},{"key":"bibr9-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1016\/j.agsy.2017.01.023"},{"key":"bibr10-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2021.110755"},{"key":"bibr11-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-021-01771-6"},{"key":"bibr12-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1016\/j.resconrec.2021.105636"},{"key":"bibr13-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1016\/j.wasman.2018.09.047"},{"key":"bibr14-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1177\/1741659020917434"},{"key":"bibr15-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3074319"},{"key":"bibr16-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1002\/jsc.2403"},{"key":"bibr17-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1093\/oxrep\/grab019"},{"key":"bibr18-15501329221105159","doi-asserted-by":"publisher","DOI":"10.2196\/23811"},{"key":"bibr19-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2021.100564"},{"key":"bibr20-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1016\/j.cej.2020.126673"},{"key":"bibr21-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2020.142876"},{"key":"bibr22-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-79408-8_21"},{"key":"bibr23-15501329221105159","doi-asserted-by":"crossref","unstructured":"Chaudhary KP, Dubey PK, Gahlot A, et al. Advances in sensors and measurements for metrological applications, 2021, https:\/\/www.researchgate.net\/publication\/353362864_Advances_in_Sensors_and_Measurements_for_Metrological_Applications","DOI":"10.1007\/s12647-021-00482-w"},{"key":"bibr24-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2021.100452"},{"key":"bibr25-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.05.004"},{"key":"bibr26-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1145\/3398394"},{"first-page":"480","volume-title":"Proceedings of the European symposium on research in computer security","author":"Tolpegin V","key":"bibr27-15501329221105159"},{"key":"bibr28-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3023126"},{"key":"bibr29-15501329221105159","doi-asserted-by":"crossref","unstructured":"Russo A, Proutiere A. Poisoning attacks against data-driven control methods, 2021, https:\/\/arxiv.org\/abs\/2103.06199","DOI":"10.23919\/ACC50511.2021.9482992"},{"key":"bibr30-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2977378"},{"first-page":"1617","volume-title":"Proceedings of the 43rd international ACM SIGIR conference on research and development in information retrieval","author":"Wadhwa S","key":"bibr31-15501329221105159"},{"volume-title":"Proceedings of the 30th USENIX security symposium (USENIX Security 21)","author":"Severi G","key":"bibr32-15501329221105159"},{"key":"bibr33-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.3003571"},{"key":"bibr34-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-020-00813-y"},{"first-page":"285","volume-title":"Proceedings of the 23rd international symposium on research in attacks, intrusions and defenses (RAID\u20192020)","author":"Carminati M","key":"bibr35-15501329221105159"},{"key":"bibr36-15501329221105159","unstructured":"Takemura T, Yanai N, Fujiwara T. Model extraction attacks against recurrent neural networks, 2020, https:\/\/arxiv.org\/abs\/2002.00123"},{"key":"bibr37-15501329221105159","unstructured":"Wu B, Yang X, Pan S, et al. Model extraction attacks on graph neural networks: taxonomy and realization, 2020, https:\/\/arxiv.org\/abs\/2010.12751"},{"key":"bibr38-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2962914"},{"first-page":"1","volume-title":"Proceedings of the 2019 IEEE global communications conference (GLOBECOM)","author":"Huang Z","key":"bibr39-15501329221105159"},{"first-page":"788","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops","author":"Truong L","key":"bibr40-15501329221105159"},{"key":"bibr41-15501329221105159","doi-asserted-by":"publisher","DOI":"10.3390\/make1010011"},{"key":"bibr42-15501329221105159","doi-asserted-by":"crossref","unstructured":"Wang J, Xu C, Guzm\u00e1n F, et al. Putting words into the system\u2019s mouth: a targeted attack on neural machine translation using monolingual data poisoning, 2021, https:\/\/arxiv.org\/abs\/2107.05243","DOI":"10.18653\/v1\/2021.findings-acl.127"},{"first-page":"1","volume-title":"Proceedings of the 2018 IEEE security and privacy workshops (SPW)","author":"Carlini N","key":"bibr43-15501329221105159"},{"first-page":"111","volume-title":"Proceedings of the 18th ACM international symposium on mobile ad hoc networking and computing","author":"Miao C","key":"bibr44-15501329221105159"},{"first-page":"969","volume-title":"Proceedings of the web conference 2021","author":"Fang M","key":"bibr45-15501329221105159"},{"first-page":"4582","volume-title":"Proceedings of the 2017 IEEE 56th annual conference on decision and control (CDC)","author":"Zhang R","key":"bibr46-15501329221105159"},{"key":"bibr47-15501329221105159","unstructured":"Biggio B, Nelson B, Laskov P. Poisoning attacks against support vector machines, 2012, https:\/\/arxiv.org\/abs\/1206.6389"},{"key":"bibr48-15501329221105159","doi-asserted-by":"publisher","DOI":"10.3390\/su12166434"},{"key":"bibr49-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-02086-4"},{"first-page":"19","volume-title":"Proceedings of the 2018 IEEE symposium on security and privacy (SP)","author":"Jagielski M","key":"bibr50-15501329221105159"},{"key":"bibr51-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-019-03968-7"},{"key":"bibr52-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.08.081"},{"key":"bibr53-15501329221105159","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-04831-9"},{"volume-title":"Proceedings of the 13th ACM conference on embedded networked sensor systems (SenSys\u20182015)","author":"Stisen A","key":"bibr54-15501329221105159"},{"first-page":"1285","volume-title":"Proceedings of the 2017 13th international wireless communications and mobile computing conference (IWCMC)","author":"Qolomany B","key":"bibr55-15501329221105159"}],"container-title":["International Journal of Distributed Sensor Networks"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/15501329221105159","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/15501329221105159","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/15501329221105159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T10:38:41Z","timestamp":1657795121000},"score":1,"resource":{"primary":{"URL":"http:\/\/journals.sagepub.com\/doi\/10.1177\/15501329221105159"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":55,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["10.1177\/15501329221105159"],"URL":"https:\/\/doi.org\/10.1177\/15501329221105159","relation":{},"ISSN":["1550-1329","1550-1477"],"issn-type":[{"type":"print","value":"1550-1329"},{"type":"electronic","value":"1550-1477"}],"subject":[],"published":{"date-parts":[[2022,7]]}}}