Information Technology Reference
In-Depth Information
y = 4.4429x + 8.3905
100
92
88
90
80
69
70
59
59
58
60
47
50
41
41
39
40
24
30
17
20
11
8
6
10
0
2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014
Year of Publication
Fig. 7 Number of articles on neural network applied intrusion detection system development
published during the year 2000
-
2014 and the research trend
articles followed by 273 articles in engineering (26 %) and 108 articles in mathe-
matics (10 %).
In Fig.
7
the research trend based on the number of articles published between
the years 2000
2013 has been shown to be increasing with R-squared value equals
0.9433 which is a good
-
2014 is also increasing
where the search on articles has been performed in February, 2014.
The next section has discussed the description of the data set applied in the
development of the model for intrusion detection system.
fit. The trend line in Fig.
7
for 2000
-
3 KDD-99 Dataset
Mostly all the experiments on intrusion detection are done on KDDCUP
99 dataset,
which is a subset of the 1998 DARPA Intrusion Detection Evaluation data set, and
is processed, extracting 41 features from the raw data of DARPA 98 data set Stolfo
et al. (
2000
)de
'
ned higher-level features that help in distinguishing between good
normal connections from bad connections (attacks). This data can be used to test
both host based and network based systems, and both signature and anomaly
detection systems. A connection is a sequence of Transmission Control Protocol
(TCP) packets starting and ending with well de
ned times, between which data
flows from a source IP address to a target IP address under some well defined
protocol. Each connection is labeled as normal, or as an attack, with exactly one
speci
c attack type. Each connection record consists of about 100 bytes (
https://
The data to be used in the model is organized and prepared to be used in the form
of binary classi
cation model needs to be
evaluated based on certain metrics from their output results and discussed in the
next section.
cation model. However the classi
Search WWH ::
Custom Search