MAGMA network behavior classifier for malware traffic

Bocchi, Enrico; Grimaudo, Luigi; Mellia, Marco; Baralis, Elena; Saha, Sabyasachi; Miskovic, Stanislav; Modelo-Howard, Gaspar; Lee, Sung-Ju

doi:10.1016/j.comnet.2016.03.021

Cited by 14 publications

(13 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Such differences can be the result of two or more different applications or behaviors, characterized by statistical properties. In some contexts, statistical distributions can be used to model the network traffic patterns [43,44,45]. On the other hand, behavioral techniques aim at finding patterns among end-toend communications in a network.…”

Section: Traffic Classification Approachesmentioning

confidence: 99%

A framework to classify heterogeneous Internet traffic with Machine Learning and Deep Learning techniques for satellite communications

Pacheco

Expósito

Gineste³

2020

Computer Networks

View full text Add to dashboard Cite

Nowadays, the Internet network system serves as a platform for communication, transaction, and entertainment, among others. This communication system is characterized by terrestrial and Satellite components that interact between themselves to provide transmission paths of information between endpoints. Particularly, Satellite Communication providers' interest is to improve customer satisfaction by optimally exploiting on demand available resources and offering Quality of Service (QoS). Improving the QoS implies to reduce errors linked to information loss and delays of Internet packets in Satellite Communications. In this sense, according to Internet traffic (Streaming, VoIP, Browsing, etc.) and those error conditions, the Internet flows can be classified into different sensitive and non-sensitive classes. Following this idea, this work aims at finding new Internet traffic classification approaches to improving the QoS. Machine Learning (ML) and Deep Learning (DL) techniques will be studied and deployed to classify Internet traffic. All the necessary elements to couple an ML or DL solution over a well-known Satellite Communication and QoS management architecture will be evaluated. To develop this solution, a rich and complete set of Internet traffic is required. In this context, an emulated Satellite Communication platform will serve as a data generation environment in which different Internet communications will be launched and captured. The proposed classification system will deal with different Internet communications (encrypted, unencrypted, and tunneled). This system will process the incoming traffic hierarchically to achieve a high classification performance. Finally, some experiments on a cloud emulated platform validates our proposal and set guidelines for its deployment over a Satellite architecture.

show abstract

Section: Traffic Classification Approachesmentioning

confidence: 99%

A framework to classify heterogeneous Internet traffic with Machine Learning and Deep Learning techniques for satellite communications

Pacheco

Expósito

Gineste³

2020

Computer Networks

View full text Add to dashboard Cite

show abstract

“…Davranışsal bir zararlı yazılım sınıflandırıcısı olan Zararlı Yazılım Tespiti için Çok Katmanlı Grafik (Multilayer Graph for Malware Detection -MAGMA) metodunun sunulduğu çalışmada [11], ağ aktivitelerinden çıkarılan desenlerin zaman, uzay ve ağ protokolü kapsamında korelasyonu yapılarak öncelikle Ağ Bağlantı Grafiği oluşturulmuş ve daha sonra bu grafikten özellik çıkarımı yapılarak bir denetimli sınıflandırıcı tasarlanmıştır. Farklı sınıflandırıcılar kullanılarak 1538 gerçekleştirilen sınıflandırmalar neticesinde en iyi sonuçların RF metoduyla alındığı görülmüş ancak çalışmanın gerçekleştirilme ortamına değinilmemiştir.…”

Section: İlgili çAlışmalarunclassified

Büyük Veri Ortamlarında Zararlı Yazılım Tespiti Kapsamında Makine Öğrenmesi Algoritmalarının Performansının İncelenmesi

Gulburun¹,

Dener²

2021

El-Cezeri Fen Ve Mühendislik Dergisi

View full text Add to dashboard Cite

Bilgi teknolojileri varlıklarının hem bireylerin günlük hayatlarındaki hem de kurum ve kuruluşların işleyişindeki yeri son çeyrek asırda hızlı bir artış göstermiş, bu artışa paralel olarak bilgi varlıklarına yönelik tehditler de artmıştır. Zararlı yazılımlar, bilgi varlıklarına yönelik başlıca tehditlerden biridir. Sürekli olarak kendini yenileyen zararlı yazılımlara karşı geleneksel tespit yaklaşımlarının yetersiz kalması sebebiyle, makine öğrenmesi modelleri kullanan tespit yaklaşımları geliştirilmiştir. Bu çalışmada, zararlı yazılım tespiti maksadıyla kullanılan farklı makine öğrenme algoritmalarının çeşitli büyük veri teknolojileri ve platformları üzerinde ortaya koydukları performanslar incelendi. Modeller, Kaggle Zararlı Yazılım Tespiti veri seti kullanılarak eğitildi. En iyi doğruluk (%98.8), kesinlik (%98.5), f1 skoru (%98.2) ve yanlış pozitif oranı (%2) performansları Google Colaboratory ortamında Sci-Kit Learn kütüphanesi ile çalıştırılan rastgele orman modeli ile elde edildi.

show abstract

“…Due to their advantages, Big Data analytics have been widely used for the detection and identification of cyberattacks in various environments. The authors in [5] presented a novel malware behavioral classifier based on the Big Data methodology. The dataset was built by collecting network traffic from an ISP.…”

Section: Background a Related Workmentioning

confidence: 99%

Big Data against Security Threats: The SPEAR Intrusion Detection System

Pliatsios¹,

Sarigiannidis²,

Psannis³

et al. 2020

2020 3rd World Symposium on Communication Engineering (WSCE)

View full text Add to dashboard Cite

The environmental concerns, the limited availability of conventional energy sources, the integration of alternative energy sources and the increasing number of powerdemanding appliances change the way electricity is generated and distributed. Smart Grid (SG) is an appealing concept, which was developed in response to the emerging issues of electricity generation and distribution. By leveraging the latest advancements of Information and Communication Technologies (ICT), it offers significant benefits to energy providers, retailers and consumers. Nevertheless, SG is vulnerable to cyber attacks, that could cause critical economic and ecological consequences. Traditional Intrusion Detection Systems (IDSs) are becoming less efficient in detecting and mitigating cyberattacks, due to their limited capabilities of analyzing the exponentially increasing volume of network traffic. In this paper, we present the Secure and PrivatE smArt gRid (SPEAR) platform, which features a Big Data enabled IDS that timely detects and identifies cyber attacks against SG components. In order to validate the efficiency of the SPEAR platform regarding the protection of critical infrastructure, we installed the platform in a small wind power plant.

show abstract

MAGMA network behavior classifier for malware traffic

Cited by 14 publications

References 23 publications

A framework to classify heterogeneous Internet traffic with Machine Learning and Deep Learning techniques for satellite communications

A framework to classify heterogeneous Internet traffic with Machine Learning and Deep Learning techniques for satellite communications

Büyük Veri Ortamlarında Zararlı Yazılım Tespiti Kapsamında Makine Öğrenmesi Algoritmalarının Performansının İncelenmesi

Big Data against Security Threats: The SPEAR Intrusion Detection System

Contact Info

Product

Resources

About