Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Sniffing Attack Detection in 6LoWPAN RPL Networks Using Machine Learning Algorithms
Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science.
2024 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

6LoWPAN also known as “IPV6 over Low Power Wireless Personal Area Network” is a standard created to make IPv6 Protocol work on even the smallest devices with limited processing capabilities. RPL also known as Routing Protocol for Low power and lossy networks is a network layer routing protocol specifically designed for 6LoPWAN. RPL is subjected to various attacks in which sniffing attack is a type of traffic packet eavesdropping attack. There is a research gap when it comes to detecting sniffing attacks on 6LoWPAN RPL networks or any detailed information about it. So, the aim of this thesis is to detect the sniffing attack in 6LoPWAN RPL networks and find which machine learning algorithm is best in detecting this type of attack. A poorly implemented sniffer can cause latency due to resource constraints which can further cause changes in data traffic pattern. Since sniffing attack can cause unauthorized authentication and further attacks like spoofing attacks,sinkhole attacks and DoS attacks, it is important to detect it. This thesis starts by trying to detect sniffing attack on small scale networks. Instantcontiki3.0 (Cooja Simulator) is used here generate network traffic for both normal scenarios and attack scenarios. The data obtained from the simulation is pre-processed to feed the machine learning algorithms. The features are extracted using chi2 feature selection method. In this thesis the ML algorithms used are Random Forest classifier, Naive Bayes classifier, Support Vector Machine, Logistic regression, K- nearest neighbor and Decision tree. From the analysis of the results, it is concluded that the Random Forest classifier is the best algorithm to detect sniffing attack. The prefix value in RPL options which are carried by ICMPv6 control messages can point theDAG partition the sniffer is located by mapping to a DODAG ID.

Place, publisher, year, edition, pages
2024. , p. 47
Keywords [en]
6LoPWAN, RPL, Sniffing attack, Machine learning, feature selection, network, eavesdropping
National Category
Telecommunications
Identifiers
URN: urn:nbn:se:bth-26746OAI: oai:DiVA.org:bth-26746DiVA, id: diva2:1886761
Subject / course
ET2606 Masterarbete i elektroteknik med inriktning mot telekommunikationssystem 30,0 hp
Educational program
ETATL Master's Programme in Telecommunication Systems
Supervisors
Examiners
Available from: 2024-08-08 Created: 2024-08-04 Last updated: 2025-09-30Bibliographically approved

Open Access in DiVA

fulltext(1178 kB)320 downloads
File information
File name FULLTEXT01.pdfFile size 1178 kBChecksum SHA-512
7aa40c9faf63537ce11108d826a0aa987bd5aad31956e8652b320dfb4dffddbbaa809bc7cf7ddaf3f73e08905e03632b0ef3075cfb8244dfeff013a87cb43e18
Type fulltextMimetype application/pdf

By organisation
Department of Computer Science
Telecommunications

Search outside of DiVA

GoogleGoogle Scholar
Total: 322 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 354 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf