Navie Bayes Intrusion Classification System for Voice over Internet ProtocolNetwork Using Honeypot

Voice over Internet Protocol (VoIP) is an emerging trend of applications on the Internet today. As withany recent technology, VoIP also introduces both fortuity and problems. Existing VoIP honeypotexperimental set ups based on SIP (Session Initiation Protocol) deals with the basic attacks like DoS(Denial of Service), enumeration detection, signature collection and SPIT (Spam over InternetTelephony). We propose a method using honeypot where Naive Bayes’ classifier is used to categorizeattack packets into VoIP MAC spoofing, SIP port scanning and VoIP service abuse attack, which arenot concentrated much in the extant prevention methods. VoIP honeypot results are treated morevaluable than the existing Intrusion Detection System (IDS) as the datasets used in IDS are predefinedand can identify only the existing pattern of attacks. But honeypot can identify attacks which originatefrom new patterns than the existing IDS. For result analysis, we propose a test-bed using Zoiper (SIPclients), Asterisk server, Artemisa honeypot and Wireshark as network packet analyzer. The test-beddemonstrates how honeypot identifies and prevents unsolicited users, thus improving the robustness ofthe VoIP system in terms of security.