DocumentCode :
726946
Title :
The energy cost of network security: A hardware vs. software comparison
Author :
Franca, Andre L. ; Jasinski, Ricardo ; Cemin, Paulo ; Pedroni, Volnei A. ; Olivo Santin, Altair
Author_Institution :
Fed. Technol. Univ. of Parana (UTFPR), Curitiba, Brazil
fYear :
2015
fDate :
24-27 May 2015
Firstpage :
81
Lastpage :
84
Abstract :
The increasing network speeds, number of attacks, and need for energy efficiency are pushing software-based network security to the limit. A common kind of threat is probing attacks, in which an attacker tries to find vulnerabilities by sending many probe packets to a target machine. In this paper, we evaluate three machine learning classifiers (Decision Tree, Naive Bayes, and k-Nearest Neighbors), implemented in hardware and software, for the detection of probing attacks. We present detailed results showing the tradeoffs between energy consumption, throughput, and accuracy of the three classifiers. The fastest hardware implementation is 926 times as fast as its software counterpart, and its energy consumption per classification is 0.05% that of the software version.
Keywords :
decision trees; energy conservation; energy consumption; learning (artificial intelligence); pattern classification; power aware computing; security of data; Naive Bayes; decision tree; energy consumption; energy cost; energy efficiency; hardware-based network security; k-nearest neighbors; machine learning classifiers; probe packets; probing attack detection; software-based network security; Accuracy; Classification algorithms; Energy consumption; Hardware; Niobium; Throughput; Training; Decision Tree; Energy Efficiency; Naive Bayes; Network Security; Probing Attack; k-Nearest Neighbors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems (ISCAS), 2015 IEEE International Symposium on
Conference_Location :
Lisbon
Type :
conf
DOI :
10.1109/ISCAS.2015.7168575
Filename :
7168575
Link To Document :
بازگشت