Evolutionary optimization of intrusion detection system in wireless sensor networks

Mgr. Adam Saleh

Diplomová práce

Anotace:

Optimalizácia IDS pre WSN býva časovo náročný proces, preto sme sa ho rozhodli urýchliť a zjednodušiť použitím multi-kriteriálnych evolučných algoritmov.

Abstract:

Intrusion detection is an essential mechanism to protect wireless sensor networks against internal attacks that are relatively easy and not expensive to mount in these networks. Setting up an intrusion detection system on network of nodes so that it satisfies constrains on accuracy, battery life and memory can be a time-consuming process. To speed up the process, we proposed to use multi-objective evolutionary algorithms, such as NSGAII or SPEA2. To simplify the setup of multi-objective optimization, we have implemented and tested a framework that combines the MiXiM simulation framework for wireless sensor networks, framework for evolutionary optimization ParadisEO and infrastructure for network computing BOINC. Our examination focuses on the impact of an evolutionary algorithm (as well as its parameters) on the optimality of found solutions and resource intensitivity of the optimization.

Keywords

IDS, NSGAII, SPEA2, IBEA, MOGA, MOEO, WSN

Jazyk práce: angličtina

Datum vytvoření / odevzdání či podání práce: 6. 1. 2014

Obhajoba závěrečné práce

• Obhajoba proběhla 11. 2. 2014
• Vedoucí: RNDr. Andrij Stecko, Ph.D.
• Oponent: RNDr. Petr Švenda, Ph.D.

Masarykova univerzita

Fakulta informatiky

Magisterský studijní program / obor:
Informatika / Bezpečnost informačních technologií