Identification of Attacks against
Wireless Sensor Networks Based on Behaviour
Analysis Grahpics Processing Units ITMO
University, St. Petersburg, Russia vika@cit.ifmo.ru,
groznykhanton@yandex.ru, menshikov@corp.ifmo.ru, martin.strecker@irit.fr Abstract The paper describes the problem of identification of
network layer attacks on wireless sensor networks for subsequent development
of intrusion detection systems. 15 types of behaviour (including 14 states
under attack and the normal state) and identification features are briefly
specified. A technique for attacks identifying based on a combination of
Random Forest algorithm and probability classifier is proposed. A study of the
dependence of the accuracy of the probability classifier and the average
number of used features on a confidence level and a priori probability of the
normal state, which allows reducing the feature space to one feature, is
described. For most attacks, there is a relative constancy of the dependence
values in the range from 0 to 0.7 ± 0.15, after which a decrease occurs,
corresponding to the quality of identification. Recommendations to the
algorithm parameters are formed and its evaluation is carried out. Keywords: wireless sensor network, information
security, attack identification, behavior analysis +: Corresponding author: Viktoriia Korzhuk Journal
of Wireless Mobile Networks, Ubiquitous Computing, and Dependable
Applications (JoWUA) Vol. 10, No. 2, pp.1-21, June 2019 [pdf] Received: April 27, 2019; Accepted: June
19, 2019; Published: June 30, 2019 |