TY - GEN
T1 - Machine learning security assessment method based on adversary and attack methods
AU - Pacheco-Rodríguez, Hugo Sebastian
AU - Aguirre-Anaya, Eleazar
AU - Menchaca-Méndez, Ricardo
AU - Medina-Llinàs, Manel
N1 - Publisher Copyright:
© 2020, Springer Nature Switzerland AG.
PY - 2020
Y1 - 2020
N2 - Analytical methods for assessing the security of Machine Learning Systems (MLS) that have been proposed in other researches do not provide compatibility with each other and their taxonomies have become incomplete due to the introduction of new properties of adversarial machine learning. In this sense, we have identified carefully relevant concepts of most prevalent researches about the security assessment of MLS. We propose a novel security assessment method based on the modeling of the adversary and the selection of adversarial attack methods for the generation of adversarial examples related to the also proposed taxonomy. This method provides compatibility with other proposed methods as well as practical guidelines and tools for evaluating machine learning systems. We also introduce the concern for efficient metrics capable of measuring the robustness of MLS to adversarial examples. This research is focused on the empirical evaluation of the security of machine learning systems, rather than on classical performance evaluation.
AB - Analytical methods for assessing the security of Machine Learning Systems (MLS) that have been proposed in other researches do not provide compatibility with each other and their taxonomies have become incomplete due to the introduction of new properties of adversarial machine learning. In this sense, we have identified carefully relevant concepts of most prevalent researches about the security assessment of MLS. We propose a novel security assessment method based on the modeling of the adversary and the selection of adversarial attack methods for the generation of adversarial examples related to the also proposed taxonomy. This method provides compatibility with other proposed methods as well as practical guidelines and tools for evaluating machine learning systems. We also introduce the concern for efficient metrics capable of measuring the robustness of MLS to adversarial examples. This research is focused on the empirical evaluation of the security of machine learning systems, rather than on classical performance evaluation.
KW - Evaluation
KW - Machine learning
KW - Security
UR - http://www.scopus.com/inward/record.url?scp=85096574282&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-62554-2_27
DO - 10.1007/978-3-030-62554-2_27
M3 - Contribución a la conferencia
AN - SCOPUS:85096574282
SN - 9783030625535
T3 - Communications in Computer and Information Science
SP - 377
EP - 389
BT - Telematics and Computing - 9th International Congress, WITCOM 2020, Proceedings
A2 - Mata-Rivera, Miguel Félix
A2 - Zagal-Flores, Roberto
A2 - Barria-Huidobro, Cristian
PB - Springer Science and Business Media Deutschland GmbH
T2 - 9th International Congress on Telematics and Computing, WITCOM 2020
Y2 - 2 November 2020 through 6 November 2020
ER -