Towards the Use of Generative Adversarial Neural Networks to Attack Online Resources
Published in Advances in Intelligent Systems and Computing, 2020
Recommended citation: Lelio Campanile, Mauro Iacono, Fabio Martinelli, Fiammetta Marulli, Michele Mastroianni, Francesco Mercaldo, Antonella Santone, "Towards the Use of Generative Adversarial Neural Networks to Attack Online Resources." Advances in Intelligent Systems and Computing, 2020. https://www.scopus.com/inward/record.uri?eid=2-s2.0-85083965494&doi=10.1007%2f978-3-030-44038-1_81&partnerID=40&md5=a31bc02a9b628120dbddc4b0286107e4
Cited by: 6
Abstract: The role of remote resources, such as the ones provided by Cloud infrastructures, is of paramount importance for the implementation of cost effective, yet reliable software systems to provide services to third parties. Cost effectiveness is a direct consequence of a correct estimation of resource usage, to be able to define a budget and estimate the right price to put own services on the market. Attacks that overload resources with non legitimate requests, being them explicit attacks or just malicious, non harmful resource engagements, may push the use of Cloud resources beyond estimation, causing additional costs, or unexpected energy usage, or a lower overall quality of services, so intrusion detection devices or firewalls are set to avoid undesired accesses. We propose the use of Generative Adversarial Neural Networks (GANs) to setup a method for shaping request based attacks capable of reaching resources beyond defenses. The approach is studied by using a publicly available traffic data set, to test the concept and demonstrate its potential applications. © 2020, Springer Nature Switzerland AG.
Author Keywords: Cloud; Deep learning; Energy attacks; Generative Adversarial Networks; Microservices; Security; Serverless; Service degradation; Software services
Bibtex citation:
@ARTICLE{Campanile2020890,
author = "Campanile, Lelio and Iacono, Mauro and Martinelli, Fabio and Marulli, Fiammetta and Mastroianni, Michele and Mercaldo, Francesco and Santone, Antonella",
title = "Towards the Use of Generative Adversarial Neural Networks to Attack Online Resources",
year = "2020",
journal = "Advances in Intelligent Systems and Computing",
volume = "1150 AISC",
pages = "890 – 901",
doi = "10.1007/978-3-030-44038-1\_81",
type = "Conference paper"
}