000135815 001__ 135815
000135815 005__ 20260112133228.0
000135815 0247_ $$2doi$$a10.1007/s11227-024-06166-x
000135815 0248_ $$2sideral$$a138855
000135815 037__ $$aART-2024-138855
000135815 041__ $$aeng
000135815 100__ $$aRuiz-Villafranca, Sergio
000135815 245__ $$aA TabPFN-based intrusion detection system for the industrial internet of things
000135815 260__ $$c2024
000135815 5060_ $$aAccess copy available to the general public$$fUnrestricted
000135815 5203_ $$aThe industrial internet of things (IIoT) has undergone rapid growth in recent years, which has resulted in an increase in the number of threats targeting both IIoT devices and their connecting technologies. However, deploying tools to counter these threats involves tackling inherent limitations, such as limited processing power, memory, and network bandwidth. As a result, traditional solutions, such as the ones used for desktop computers or servers, cannot be applied directly in the IIoT, and the development of new technologies is essential to overcome this issue. One approach that has shown potential for this new paradigm is the implementation of intrusion detection system (IDS) that rely on machine learning (ML) techniques. These IDSs can be deployed in the industrial control system or even at the edge layer of the IIoT topology. However, one of their drawbacks is that, depending on the factory’s specifications, it can be quite challenging to locate sufficient traffic data to train these models. In order to address this problem, this study introduces a novel IDS based on the TabPFN model, which can operate on small datasets of IIoT traffic and protocols, as not in general much traffic is generated in this environment. To assess its efficacy, it is compared against other ML algorithms, such as random forest, XGBoost, and LightGBM, by evaluating each method with different training set sizes and varying numbers of classes to classify. Overall, TabPFN produced the most promising outcomes, with a 10–20% differentiation in each metric. The best performance was observed when working with 1000 training set samples, obtaining an F1 score of 81% for 6-class classification and 72% for 10-class classification.
000135815 536__ $$9info:eu-repo/grantAgreement/ES/DGA/T21-23R$$9info:eu-repo/grantAgreement/ES/MICINN/PID2021-123627OB-C52$$9info:eu-repo/grantAgreement/EUR/MICINN/TED2021-131115A-I00
000135815 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttps://creativecommons.org/licenses/by/4.0/deed.es
000135815 590__ $$a2.7$$b2024
000135815 592__ $$a0.716$$b2024
000135815 591__ $$aCOMPUTER SCIENCE, HARDWARE & ARCHITECTURE$$b27 / 60 = 0.45$$c2024$$dQ2$$eT2
000135815 593__ $$aHardware and Architecture$$c2024$$dQ2
000135815 591__ $$aENGINEERING, ELECTRICAL & ELECTRONIC$$b167 / 366 = 0.456$$c2024$$dQ2$$eT2
000135815 593__ $$aTheoretical Computer Science$$c2024$$dQ2
000135815 591__ $$aCOMPUTER SCIENCE, THEORY & METHODS$$b51 / 147 = 0.347$$c2024$$dQ2$$eT2
000135815 593__ $$aSoftware$$c2024$$dQ2
000135815 593__ $$aInformation Systems$$c2024$$dQ2
000135815 594__ $$a7.1$$b2024
000135815 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000135815 700__ $$aRoldán-Gómez, José
000135815 700__ $$aCastelo Gómez, Juan Manuel
000135815 700__ $$aCarrillo-Mondéjar, Javier$$uUniversidad de Zaragoza
000135815 700__ $$aMartinez, José Luis
000135815 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Lenguajes y Sistemas Inf.
000135815 773__ $$g80 (2024), 20080–20117$$pJ. supercomput.$$tJournal of Supercomputing$$x0920-8542
000135815 8564_ $$s2402170$$uhttps://zaguan.unizar.es/record/135815/files/texto_completo.pdf$$yVersión publicada
000135815 8564_ $$s1335953$$uhttps://zaguan.unizar.es/record/135815/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000135815 909CO $$ooai:zaguan.unizar.es:135815$$particulos$$pdriver
000135815 951__ $$a2026-01-12-12:48:32
000135815 980__ $$aARTICLE