A Neural Network Based System for Classification of Attacks in IP Telephony

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F63839172%3A_____%2F14%3A10130425" target="_blank" >RIV/63839172:_____/14:10130425 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

A Neural Network Based System for Classification of Attacks in IP Telephony

Popis výsledku v původním jazyce

This article deals with an application of artificial intelligence on classification of attacks in IP telephony. Current used solution of classification is typically based on statistical methods such as Hellinger-Distance, Holt-Winters or Brutlag algorithm and the proposed solution MLP NN in the paper is used as a classifier of attacks in a distributed monitoring network of independent honeypot probes. The vulnerability of SIP elements to DoS attacks was examined in real infrastructure and evaluated their impact on a SIP server. We prepared a set of honeypots monitoring various aspects of nowadays VoIP infrastructure which bring valuable data about hacker's activity with no threat to the running system. Data about attacks on these honeypots are collected on a centralized server and then classified in the neural network. The paper describes inner structure of used neural network and also information about implementation of this network. The trained neural network is capable to classify t

Název v anglickém jazyce

A Neural Network Based System for Classification of Attacks in IP Telephony

Popis výsledku anglicky

This article deals with an application of artificial intelligence on classification of attacks in IP telephony. Current used solution of classification is typically based on statistical methods such as Hellinger-Distance, Holt-Winters or Brutlag algorithm and the proposed solution MLP NN in the paper is used as a classifier of attacks in a distributed monitoring network of independent honeypot probes. The vulnerability of SIP elements to DoS attacks was examined in real infrastructure and evaluated their impact on a SIP server. We prepared a set of honeypots monitoring various aspects of nowadays VoIP infrastructure which bring valuable data about hacker's activity with no threat to the running system. Data about attacks on these honeypots are collected on a centralized server and then classified in the neural network. The paper describes inner structure of used neural network and also information about implementation of this network. The trained neural network is capable to classify t

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/LM2010005" target="_blank" >LM2010005: Velká infrastruktura CESNET</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2014

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

INTERNATIONAL JOURNAL OF CIRCUITS, SYSTEMS AND SIGNAL PROCESSING

ISSN

1998-4464

e-ISSN

—

Svazek periodika

8

Číslo periodika v rámci svazku

neuveden

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

8

Strana od-do

368-375

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—