Cargando…

Arhuaco: Deep Learning and Isolation Based Security for Distributed High-Throughput Computing

Grid computing systems require innovative methods and tools to identify cybersecurity incidents and perform autonomous actions i.e. without administrator intervention. They also require methods to isolate and trace job payload activity in order to protect users and find evidence of malicious behavio...

Descripción completa

Detalles Bibliográficos
Autores principales: Gomez Ramirez, A., Lara, C., Betev, L., Bilanovic, D., Kebschull, U.
Lenguaje:eng
Publicado: 2018
Materias:
Acceso en línea:http://cds.cern.ch/record/2300286
_version_ 1780957086881939456
author Gomez Ramirez, A.
Lara, C.
Betev, L.
Bilanovic, D.
Kebschull, U.
author_facet Gomez Ramirez, A.
Lara, C.
Betev, L.
Bilanovic, D.
Kebschull, U.
author_sort Gomez Ramirez, A.
collection CERN
description Grid computing systems require innovative methods and tools to identify cybersecurity incidents and perform autonomous actions i.e. without administrator intervention. They also require methods to isolate and trace job payload activity in order to protect users and find evidence of malicious behavior. We introduce an integrated approach of security monitoring via Security by Isolation with Linux Containers and Deep Learning methods for the analysis of real time data in Grid jobs running inside virtualized High-Throughput Computing infrastructure in order to detect and prevent intrusions. A dataset for malware detection in Grid computing is described. We show in addition the utilization of generative methods with Recurrent Neural Networks to improve the collected dataset. We present Arhuaco, a prototype implementation of the proposed methods. We empirically study the performance of our technique. The results show that Arhuaco outperforms other methods used in Intrusion Detection Systems for Grid Computing. The study is carried out in the ALICE Collaboration Grid, part of the Worldwide LHC Computing Grid.
id cern-2300286
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2018
record_format invenio
spelling cern-23002862023-06-29T03:47:01Zhttp://cds.cern.ch/record/2300286engGomez Ramirez, A.Lara, C.Betev, L.Bilanovic, D.Kebschull, U.Arhuaco: Deep Learning and Isolation Based Security for Distributed High-Throughput Computingcs.LGComputing and Computerscs.CRComputing and Computerscs.DCComputing and ComputersGrid computing systems require innovative methods and tools to identify cybersecurity incidents and perform autonomous actions i.e. without administrator intervention. They also require methods to isolate and trace job payload activity in order to protect users and find evidence of malicious behavior. We introduce an integrated approach of security monitoring via Security by Isolation with Linux Containers and Deep Learning methods for the analysis of real time data in Grid jobs running inside virtualized High-Throughput Computing infrastructure in order to detect and prevent intrusions. A dataset for malware detection in Grid computing is described. We show in addition the utilization of generative methods with Recurrent Neural Networks to improve the collected dataset. We present Arhuaco, a prototype implementation of the proposed methods. We empirically study the performance of our technique. The results show that Arhuaco outperforms other methods used in Intrusion Detection Systems for Grid Computing. The study is carried out in the ALICE Collaboration Grid, part of the Worldwide LHC Computing Grid.arXiv:1801.04179oai:cds.cern.ch:23002862018
spellingShingle cs.LG
Computing and Computers
cs.CR
Computing and Computers
cs.DC
Computing and Computers
Gomez Ramirez, A.
Lara, C.
Betev, L.
Bilanovic, D.
Kebschull, U.
Arhuaco: Deep Learning and Isolation Based Security for Distributed High-Throughput Computing
title Arhuaco: Deep Learning and Isolation Based Security for Distributed High-Throughput Computing
title_full Arhuaco: Deep Learning and Isolation Based Security for Distributed High-Throughput Computing
title_fullStr Arhuaco: Deep Learning and Isolation Based Security for Distributed High-Throughput Computing
title_full_unstemmed Arhuaco: Deep Learning and Isolation Based Security for Distributed High-Throughput Computing
title_short Arhuaco: Deep Learning and Isolation Based Security for Distributed High-Throughput Computing
title_sort arhuaco: deep learning and isolation based security for distributed high-throughput computing
topic cs.LG
Computing and Computers
cs.CR
Computing and Computers
cs.DC
Computing and Computers
url http://cds.cern.ch/record/2300286
work_keys_str_mv AT gomezramireza arhuacodeeplearningandisolationbasedsecurityfordistributedhighthroughputcomputing
AT larac arhuacodeeplearningandisolationbasedsecurityfordistributedhighthroughputcomputing
AT betevl arhuacodeeplearningandisolationbasedsecurityfordistributedhighthroughputcomputing
AT bilanovicd arhuacodeeplearningandisolationbasedsecurityfordistributedhighthroughputcomputing
AT kebschullu arhuacodeeplearningandisolationbasedsecurityfordistributedhighthroughputcomputing