• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ºÒ±ÕÇü À¥ ¾îÇø®ÄÉÀÌ¼Ç °ø°Ý ŽÁö¸¦ À§ÇÑ CNN ±â¹Ý Àúº¹Àâµµ ÆÇÁ¤ ½Å·Úµµ ÃßÁ¤
¿µ¹®Á¦¸ñ(English Title) CNN-based Reduced Complexity Decision Confidence Estimation for Imbalanced Web Application Attack Detection
ÀúÀÚ(Author) ¹Ú½Â¿µ   ±èÇѼº   Á¤ÅÂÁØ   Seungyoung Park   Hansung Kim   Taejoon Jung  
¿ø¹®¼ö·Ïó(Citation) VOL 47 NO. 09 PP. 0842 ~ 0852 (2020. 09)
Çѱ۳»¿ë
(Korean Abstract)
ÃÖ±Ù À¥ ¾îÇø®ÄÉÀÌ¼Ç °ø°ÝÀÇ ±Þ°ÝÇÑ Áõ°¡¿Í ÇÔ²² ±× Á¾·ù°¡ ´Ù¾çÇØÁü¿¡ µû¶ó ±âÁ¸ÀÇ ±â¹ýµé¸¸À¸·Î´Â À̸¦ ŽÁöÇÏ´Â °Í¿¡ ÇÑ°è°¡ ÀÖ¾ú´Ù. ÀÌ·¯ÇÑ ¹®Á¦¸¦ ÇØ°áÇϱâ À§ÇØ convolutional neural network (CNN) °ú °°Àº ±â°è ÇнÀÀ» ÀÌ¿ëÇÑ Å½Áö ±â¹ýÀÌ Á¦¾ÈµÇ¾úÀ¸³ª, ÀÌ·¯ÇÑ Å½Áö ±â¹ýÀº ÆÇÁ¤ ¿À·ù »ùÇÿ¡ ´ëÇÑ ÆÇÁ¤ÀÇ ½Å·Úµµ°¡ ³·´Ù´Â ´ÜÁ¡ÀÌ ÀÖ´Ù. ÀÌ ¹®Á¦¸¦ ÇØ°áÇϱâ À§ÇØ, Monte-Carlo batch normalization (MCBN) ±â¹ýÀÌ Á¦¾ÈµÇ¾ú´Ù. ±¸Ã¼ÀûÀ¸·Î, MCBN ±â¹ýÀº ÀÓÀÇÀÇ ÆÇÁ¤ÇÒ »ùÇÃÀÌ Æ÷ÇÔµÈ ¼­·Î ´Ù¸¥ mini-batchµéÀ» CNNÀ» ÀÌ¿ëÇÏ¿© ¹Ýº¹ ÆÇÁ¤À» ¼öÇàÇÏ°í ÀÌ °á°ú¸¦ Æò±ÕÇÏ¿© ÆÇÁ¤ ½Å·Úµµ¸¦ ÃßÁ¤ÇÑ´Ù. ±×·¯³ª ÀÌ ±â¹ý¿¡¼­´Â mini-batch ¸¦ ±¸¼ºÇÏ´Â M°³ÀÇ µ¥ÀÌÅÍ Áß ÇϳªÀÇ ÆÇÁ¤ µ¥ÀÌÅ͸¦ Á¦¿ÜÇÑ ¸ðµç µ¥ÀÌÅÍ¿¡ ÈÆ·Ã µ¥ÀÌÅ͸¦ »ç¿ëÇϱ⠶§¹®¿¡ ¸¹Àº ¿¬»êÀÌ ¿ä±¸µÈ´Ù. µû¶ó¼­ º» ³í¹®¿¡¼­´Â ºÒ±ÕÇü À¥ ¾îÇø®ÄÉÀÌ¼Ç °ø°Ý ŽÁö¸¦ À§ÇÑ Àúº¹Àâµµ ÆÇÁ¤ ½Å·Úµµ ÃßÁ¤ ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾È ±â¹ýÀº ÆÇÁ¤À» À§ÇÑ mini-batch ±¸¼º ½Ã, Á¤»ó ¹× °ø°Ý »ùÇà ±¸¼º ºñÀ²À» ÈÆ·Ã °úÁ¤¿¡¼­ÀÇ ºñÀ²°ú µ¿ÀÏÇÏ°Ô À¯ÁöÇÑ´Ù. À̸¦ À§ÇØ ÆÇÁ¤ µ¥ÀÌÅÍ¿¡ ´ëÇÑ Àӽà ÆÇÁ¤À» ÀÌ¿ëÇÏ¿© ´ë·«ÀûÀΠŬ·¡½º °£ ºñÀ²À» È®ÀÎÇÏ°í ºÎÁ·ÇÑ Å¬·¡½º µ¥ÀÌÅ͸¦ ÈÆ·Ã µ¥ÀÌÅͷκÎÅÍ °ú´ëÇ¥Áý ÇÏ¿´´Ù. À̸¦ ÅëÇØ Á¦¾È ±â¹ýÀº MCBN ±â¹ý¿¡ ºñÇØ °è»ê·®À» ÃÖ´ë M¹è±îÁö ÁÙ¿´´Ù. ¸ðÀÇ ½ÇÇè °á°ú·ÎºÎÅÍ, MCBN ±â¹ý°ú ºñ±³ÇÏ¿© ÆÇÁ¤ ¼º´ÉÀÌ Çâ»óµÇ¾ú°í ÆÇÁ¤ ½Å·Úµµ ¼º´ÉÀúÇÏ°¡ Å©Áö ¾ÊÀº °ÍÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
As web application attacks have been rapidly increasing and their types have been diversified, there are limitations on detecting them with the existing schemes. To resolve this problem, the detection techniques using machine learning such as the convolutional neural network (CNN) have been proposed. However, the confidence on the decision error sample in these techniques has been unreliable. To estimate more reliable decision confidence, the Monte-Carlo batch normalization (MCBN) technique combined with the CNN has been proposed. In particular, the CNN performs multiple decisions on a given evaluation sample using multiple mini-batches containing it. Then, its decision confidence estimate is obtained by averaging the multiple decision results. However, it requires too large of a computational load. The reason is that each mini-batch comprises randomly selected (M-1) training samples and only one evaluation sample, when the mini-batch size is M. In this paper, we propose a reduced complexity decision confidence estimation scheme for imbalanced web application attack detection. Specifically, the proposed scheme reduces the computational load by up to M times compared to the MCBN scheme. Also, at the estimation process, the ratio of normal and attack samples in the mini-batch should be maintained the same as that of the training process. To achieve this, we found which class size was small by performing a temporal decision on the evaluation samples. Then, the small class was over-sampled using the training samples to maintain the ratio. Our experimental results showed that the performance improved, and the reliability estimation performance was not significantly degraded compared to the MCBN scheme.
Å°¿öµå(Keyword) ¸óÅ×Ä«¸¦·Î¹èÄ¡Á¤±ÔÈ­   ºÒÈ®½Ç¼º   ½Å·Ú¼º   ÄÁº¼·ç¼Ç ½Å°æ¸Á   Ŭ·¡½º ºÒ±ÕÇü   À¥ ¾îÇø®ÄÉÀ̼Ǡ  Monte-Carlo batch normalization   uncertainty   confidence   convolutional neural network   class imbalance   web application  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå