A hybrid system for malware detection on big data

Risultato della ricerca: Other

5 Citazioni (Scopus)

Abstract

In recent years, the increasing diffusion of malicious software has encouraged the adoption of advanced machine learning algorithms to timely detect new threats. A cloud-based approach allows to exploit the big data produced by client agents to train such algorithms, but on the other hand, poses severe challenges on their scalability and performance. We propose a hybrid cloud-based malware detection system in which static and dynamic analyses are combined in order to find a good trade-off between response time and detection accuracy. Our system performs a continuous learning process of its models, based on deep networks, by exploiting the growing amount of data provided by clients. The preliminary experimental evaluation confirms the suitability of the approach proposed here.
Lingua originaleEnglish
Pagine45-50
Numero di pagine6
Stato di pubblicazionePublished - 2018

Fingerprint

Malware
Hybrid systems
Hybrid Systems
Learning Process
Experimental Evaluation
Learning algorithms
Response Time
Learning systems
Scalability
Learning Algorithm
Machine Learning
Trade-offs
Model-based
Software
Big data

All Science Journal Classification (ASJC) codes

  • Control and Optimization
  • Artificial Intelligence
  • Computer Networks and Communications

Cita questo

@conference{6c2738da4ae141ec902ff10aac219fcd,
title = "A hybrid system for malware detection on big data",
abstract = "In recent years, the increasing diffusion of malicious software has encouraged the adoption of advanced machine learning algorithms to timely detect new threats. A cloud-based approach allows to exploit the big data produced by client agents to train such algorithms, but on the other hand, poses severe challenges on their scalability and performance. We propose a hybrid cloud-based malware detection system in which static and dynamic analyses are combined in order to find a good trade-off between response time and detection accuracy. Our system performs a continuous learning process of its models, based on deep networks, by exploiting the growing amount of data provided by clients. The preliminary experimental evaluation confirms the suitability of the approach proposed here.",
author = "Marco Morana and {Lo Re}, Giuseppe and {De Paola}, Alessandra and Salvatore Gaglio",
year = "2018",
language = "English",
pages = "45--50",

}

TY - CONF

T1 - A hybrid system for malware detection on big data

AU - Morana, Marco

AU - Lo Re, Giuseppe

AU - De Paola, Alessandra

AU - Gaglio, Salvatore

PY - 2018

Y1 - 2018

N2 - In recent years, the increasing diffusion of malicious software has encouraged the adoption of advanced machine learning algorithms to timely detect new threats. A cloud-based approach allows to exploit the big data produced by client agents to train such algorithms, but on the other hand, poses severe challenges on their scalability and performance. We propose a hybrid cloud-based malware detection system in which static and dynamic analyses are combined in order to find a good trade-off between response time and detection accuracy. Our system performs a continuous learning process of its models, based on deep networks, by exploiting the growing amount of data provided by clients. The preliminary experimental evaluation confirms the suitability of the approach proposed here.

AB - In recent years, the increasing diffusion of malicious software has encouraged the adoption of advanced machine learning algorithms to timely detect new threats. A cloud-based approach allows to exploit the big data produced by client agents to train such algorithms, but on the other hand, poses severe challenges on their scalability and performance. We propose a hybrid cloud-based malware detection system in which static and dynamic analyses are combined in order to find a good trade-off between response time and detection accuracy. Our system performs a continuous learning process of its models, based on deep networks, by exploiting the growing amount of data provided by clients. The preliminary experimental evaluation confirms the suitability of the approach proposed here.

UR - http://hdl.handle.net/10447/304130

UR - http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8401302

M3 - Other

SP - 45

EP - 50

ER -