TY  - JOUR
T1  - Datamining and Intrusion Detection Using Back-Propagation Algorithm for Intrusion Detection
AU - , E. Anbalagan AU - , C. Puttamadappa AU - , E. Mohan AU - , B. Jayaraman AU - , Srinivasarao Madane 
JO  - International Journal of Soft Computing
VL  - 3
IS  - 4
SP  - 264
EP  - 270
PY  - 2008
DA  - 2001/08/19
SN  - 1816-9503
DO  - ijscomp.2008.264.270
UR  - https://makhillpublications.co/view-article.php?doi=ijscomp.2008.264.270
KW  - Datamining
KW  -intrusion detection
KW  -neural network
KW  -signature
KW  -back-propagation algorithm
AB  - Transmission of data over the internet keeps on increasing. The need to protect connected systems also increasing. Intrusion Detection Systems (IDSs) are the latest technology used for this purpose. Datamining plays an important role in matching intrusions with the data stored in the system. Although the field of IDSs is still developing, the systems that do exist are still not complete, in the sense that they are not able to detect all types of intrusions. Some attacks which are detected by various tools available today cannot be detected by other products, depending on the types and methods that they are built on. In this research, an artificial neural network using back-propagation algorithm has been used to implement the IDS. Inspite of much related work had been done, this study elucidates the implementation aspects of BPA for a real_ time IDS.Thousand packet information both normal and intrusion have been considered for implementation. The result of ID is very close to 99%. The topology of the ANN is (41×10×1). The network converged with 550 iterations. Very huge amount of packets are to be evaluated to know the complete performance of the developed system.
ER  -