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

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ÀÌ»ó ŽÁö ºÐ¼®¿¡¼­ ¾Ë·ÁÁöÁö ¾Ê´Â °ø°ÝÀ» ½Äº°Çϱâ À§ÇÑ ÀÌ»ê ¿þÀÌºí¸´ º¯È¯ Àû¿ë ¿¬±¸
¿µ¹®Á¦¸ñ(English Title) Application of Discrete Wavelet Transforms to Identify Unknown Attacks in Anomaly Detection Analysis
ÀúÀÚ(Author) ÀåÀ¯Áø   ±èÁö¿µ   ÀÌÁÖÇö   Ȳ ÁØ   Yoo-jin Jang   Ji-yeong Kim   Ju-hyun Lee   Jun Hwang   ±èµ¿¿í   ½Å°ÇÀ±   À±Áö¿µ   ±è»ó¼ö   ÇÑ¸í¹¬   Dong-Wook Kim   Gun-Yoon Shin   Ji-Young Yun   Sang-Soo Kim   Myung-Mook Han  
¿ø¹®¼ö·Ïó(Citation) VOL 22 NO. 03 PP. 0045 ~ 0052 (2021. 06)
Çѱ۳»¿ë
(Korean Abstract)
»çÀ̹ö º¸¾ÈÀÇ Ä§ÀÔŽÁö ½Ã½ºÅÛ¿¡¼­ ¾Ë·ÁÁöÁö ¾Ê´Â °ø°ÝÀ» ½Äº°Çϱâ À§ÇÑ ¸¹Àº ¿¬±¸°¡ ÀÌ·ç¾îÁö°í ÀÖÁö¸¸, ±× Áß¿¡¼­µµ ÀÌ»óÄ¡¸¦ ±â¹ÝÀ¸·Î ÇÏ´Â ¿¬±¸°¡ ÁÖ¸ñ¹Þ°í ÀÖ´Ù. ÀÌ¿¡ µû¶ó ¿ì¸®´Â ¾Ë·ÁÁöÁö ¾Ê´Â °ø°Ý¿¡ ´ëÇÑ ¹üÁÖ¸¦ Á¤ÀÇÇÏ¿© ÀÌ»óÄ¡¸¦ ½Äº°ÇÑ´Ù. ¾Ë·ÁÁöÁö ¾Ê´Â °ø°ÝÀº 2°¡Áö ¹üÁÖ·Î Á¶»çÇÏ¿´´Âµ¥, ù°´Â º¯Á¾ °ø°ÝÀ» »ý¼ºÇÏ´Â »çÇ×ÀÌ ÀÖ°í, µÎ ¹ø°´Â »õ·Î¿î À¯ÇüÀ¸·Î ºÐ·ùÇÏ´Â ¿¬±¸·Î ³ª´©¾ú´Ù. ¿ì¸®´Â º¯Á¾ °ø°ÝÀ» »ý¼ºÇÏ´Â ¿¬±¸ ¹üÁÖ¿¡¼­ º¯Á¾°ú °°ÀÌ À¯»ç µ¥ÀÌÅ͸¦ ½Äº°ÇÒ ¼ö ÀÖ´Â ÀÌ»óÄ¡ ¿¬±¸¸¦ ¼öÇàÇÏ¿´´Ù. ħÀÔŽÁö ½Ã½ºÅÛ¿¡¼­ ÀÌ»óÄ¡¸¦ ½Äº°ÇÏ´Â Å« ¹®Á¦´Â Á¤»óÇൿ°ú °ø°ÝÇൿÀÌ °°Àº °ø°£À» °øÀ¯ÇÏ´Â °ÍÀÌ´Ù. À̸¦ À§ÇØ ¿ì¸®´Â ÀÌ»ê ¿þÀÌºí¸´ º¯È¯À¸·Î Á¤»ó°ú °ø°Ý¿¡ ´ëÇØ ¸íÈ®ÇÑ À¯ÇüÀ¸·Î ³ª´­ ¼ö ÀÖ´Â ±â¹ýÀ» Àû¿ëÇÏ°í ÀÌ»óÄ¡¸¦ ŽÁöÇÏ¿´´Ù. °á°ú·Î ¿ì¸®´Â ÀÌ»ê ¿þÀÌºí¸´ º¯È¯À¸·Î À籸¼ºµÈ µ¥ÀÌÅÍ¿¡¼­ One-Class SVMÀ» ÅëÇÑ ÀÌ»óÄ¡¸¦ ½Äº° ÇÒ ¼ö ÀÖÀ½À» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Although many studies have been conducted to identify unknown attacks in cyber security intrusion detection systems, studies based on outliers are attracting attention. Accordingly, we identify outliers by defining categories for unknown attacks. The unknown attacks were investigated in two categories: first, there are factors that generate variant attacks, and second, studies that classify them into new types. We have conducted outlier studies that can identify similar data, such as variants, in the category of studies that generate variant attacks. The big problem of identifying anomalies in the intrusion detection system is that normal and aggressive behavior share the same space. For this, we applied a technique that can be divided into clear types for normal and attack by discrete wavelet transformation and detected anomalies. As a result, we confirmed that the outliers can be identified through One-Class SVM in the data reconstructed by discrete wavelet transform.
Å°¿öµå(Keyword) iOS   Semantic Segmentation   ±íÀÌ   ¿µ»ó󸮠  µà¾óÄ«¸Þ¶ó   ¸ð¹ÙÀÏ ¾ÖÇø®ÄÉÀ̼Ǡ  iOS   Semantic Segmentation   Depth   Computer Vision   Dual Camera   Mobile Application   ¾Ë·ÁÁöÁö ¾Ê´Â °ø°Ý   ÀÌ»ê ¿þÀÌºí¸´ º¯È¯   ÀÌ»ó ŽÁö   One-Class SVM   Unknown Attack   discrete wavelet transform   Anomaly Detection   One-Class SVM  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå