VAASI: Crafting valid and abnormal adversarial samples for anomaly detection systems in industrial scenarios

Perales Gómez, Ángel Luis; Fernández Maimó, Lorenzo; García Clemente, Félix J.; Huertas Celdrán, Alberto

Publication:
VAASI: Crafting valid and abnormal adversarial samples for anomaly detection systems in industrial scenarios

dc.contributor.author	Perales Gómez, Ángel Luis
dc.contributor.author	Fernández Maimó, Lorenzo
dc.contributor.author	García Clemente, Félix J.
dc.contributor.author	Huertas Celdrán, Alberto
dc.contributor.department	Ingeniería y Tecnología de Computadores
dc.date.accessioned	2024-06-28T08:17:52Z
dc.date.available	2024-06-28T08:17:52Z
dc.date.issued	2023-12
dc.description	© 2023 The Author(s). This manuscript version is made available under the CC-BY 4.0 license http://creativecommons.org/licenses/by/4.0/ This document is the Published version of a Published Work that appeared in final form in Journal of Information Security and Applications. To access the final edited and published work see https://doi.org/10.1016/j.jisa.2023.103647
dc.description.abstract	In the realm of industrial anomaly detection, machine and deep learning models face a critical vulnerability to adversarial attacks. In this context, existing attack methodologies primarily target continuous features, often in the context of images, making them unsuitable for the categorical or discrete features prevalent in industrial systems. To fortify the cybersecurity of industrial environments, this paper introduces a groundbreaking adversarial attack approach tailored to the unique demands of these settings. Our novel technique enables the creation of targeted adversarial samples that are valid within the framework of supervised cyberattack detection models in industrial scenarios, preserving the consistency of discrete values and correcting cases where an adversarial sample transitions into a normal one. Our approach leverages the SHAP interpretability method to identify the most salient features for each sample. Subsequently, the Projected Gradient Descent technique is employed to perturb continuous features, ensuring adversarial sample generation. To handle categorical features for a specific adversarial sample, our method scrutinizes the closest sample within the normal training dataset and replicates its categorical feature values. Additionally, Decision Trees trained within a Random Forest are utilized to ensure that the resulting adversarial samples maintain the essential abnormal behavior required for detection. The validation of our proposal was conducted using the WADI dataset obtained from a water distribution plant, providing a realistic industrial context. During validation, we assessed the mean error and the total number of adversarial samples generated by our approach, comparing it with the original Projected Gradient Descent method and the Carlini & Wagner attack across various parameter configurations. Remarkably, our proposal consistently achieved the best trade-off between mean error and the number of generated adversarial samples, showcasing its superiority in safeguarding industrial systems.	es
dc.format	application/pdf	es
dc.format.extent	13
dc.identifier.citation	Journal of Information Security and Applications, 2023, Vol. 79: 103647
dc.identifier.doi	https://doi.org/10.1016/j.jisa.2023.103647
dc.identifier.issn	Electronic: 2214-2126
dc.identifier.uri	http://hdl.handle.net/10201/142734
dc.language	eng	es
dc.publisher	Elsevier
dc.relation	This work has been funded under Grant TED2021-129300B-I00, by MCIN/AEI/10.13039/501100011033, NextGenerationEU/PRTR, UE, Grant PID2021-122466OB-I00, by MCIN/AEI/10.13039/501100011033/FEDER, UE, by the strategic project DEFENDER from the Spanish National Institute of Cybersecurity (INCIBE), by the Recovery, Transformation and Resilience Plan, Next Generation EU, by the Swiss Federal Office for Defense Procurement (armasuisse) with the CyberForce (CYD-C-2020003), and by the University of Zurich (UZH) .	es
dc.relation.publisherversion	https://www.sciencedirect.com/science/article/pii/S2214212623002314?via%3Dihub
dc.rights	info:eu-repo/semantics/openAccess	es
dc.rights	Atribución 4.0 Internacional	*
dc.rights.uri	http://creativecommons.org/licenses/by/4.0/	*
dc.subject	Adversarial attacks
dc.subject	Anomaly detection
dc.subject	Deep learning
dc.subject	Explainable artificial intelligence
dc.subject	Industrial control systems
dc.title	VAASI: Crafting valid and abnormal adversarial samples for anomaly detection systems in industrial scenarios	es
dc.type	info:eu-repo/semantics/article	es
dspace.entity.type	Publication	es
relation.isAuthorOfPublication	155e7fdb-63ef-47a4-8068-bc025cfbabb9
relation.isAuthorOfPublication.latestForDiscovery	155e7fdb-63ef-47a4-8068-bc025cfbabb9