• 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¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document : 6 / 22,712 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ¸¶ÀÌÅÍ ¾îÅðú ¸Ó½Å·¯´×À» ÀÌ¿ëÇÑ UNSW-NB15 µ¥ÀÌÅͼ ±â¹Ý À¯ÇØ Æ®·¡ÇÈ ºÐ·ù
¿µ¹®Á¦¸ñ(English Title) Malicious Traffic Classification Using Mitre ATT&CK and Machine Learning Based on UNSW-NB15 Dataset
ÀúÀÚ(Author) À±µ¿Çö   ±¸ÀÚȯ   ¿øµ¿È£   Yoon Dong Hyun   Koo Ja Hwan   Won Dong Ho  
¿ø¹®¼ö·Ïó(Citation) VOL 12 NO. 02 PP. 0099 ~ 0110 (2023. 02)
Çѱ۳»¿ë
(Korean Abstract)
º» ¿¬±¸´Â Çö º¸¾È °üÁ¦ ½Ã½ºÅÛÀÌ Á÷¸éÇÑ ½Ç½Ã°£ Æ®·¡ÇÈ Å½Áö ¹®Á¦¸¦ ÇØ°áÇϱâ À§ÇØ »çÀ̹ö À§Çù ÇÁ·¹ÀÓ¿öÅ©ÀÎ ¸¶ÀÌÅÍ ¾îÅðú ¸Ó½Å·¯´×À» ÀÌ¿ëÇÏ¿© À¯ÇØ ³×Æ®¿öÅ© Æ®·¡ÇÈÀ» ºÐ·ùÇÏ´Â ¹æ¾ÈÀ» Á¦¾ÈÇÏ¿´´Ù. ¸¶ÀÌÅÍ ¾îÅà ÇÁ·¹ÀÓ¿öÅ©¿¡ ³×Æ®¿öÅ© Æ®·¡ÇÈ µ¥ÀÌÅͼÂÀÎ UNSW-NB15¸¦ Àû¿ëÇÏ¿© ¶óº§À» º¯È¯ ÈÄ Èñ¼Ò Ŭ·¡½º 󸮸¦ ÅëÇØ ÃÖÁ¾ µ¥ÀÌÅͼÂÀ» »ý¼ºÇÏ¿´´Ù. »ý¼ºµÈ ÃÖÁ¾ µ¥ÀÌÅͼÂÀ» »ç¿ëÇÏ¿© ºÎ½ºÆà ±â¹ÝÀÇ ¾Ó»óºí ¸ðµ¨À» ÇнÀ½ÃŲ ÈÄ ÀÌ·¯ÇÑ ¾Ó»óºí ¸ðµ¨µéÀÌ ´Ù¾çÇÑ ¼º´É ÃøÁ¤ ÁöÇ¥·Î ¾î¶»°Ô ³×Æ®¿öÅ© Æ®·¡ÇÈÀ» ºÐ·ùÇÏ´ÂÁö Æò°¡ÇÏ¿´´Ù. ±× °á°ú F-1 ½ºÄھ ±âÁØÀ¸·Î Æò°¡ÇÏ¿´À» ¶§ Èñ¼Ò Ŭ·¡½º ¹Ìó¸®ÇÑ XGBoost°¡ ¸ÖƼ Ŭ·¡½º Æ®·¡ÇÈ È¯°æ¿¡¼­ °¡Àå ¿ì¼öÇÔÀ» º¸¿´´Ù. ÇнÀÇϱ⠾î·Á¿î ¼Ò¼öÀÇ °ø°ÝŬ·¡½º±îÁö Æ÷ÇÔÇÏ¿© ¸¶ÀÌÅÍ ¾îÅà ¶óº§ º¯È¯ ¹× ¿À¹ö»ùÇøµÃ³¸®¸¦ ÅëÇÑ ¸Ó½Å·¯´×Àº ±âÁ¸ ¿¬±¸ ´ëºñ Â÷º°Á¡À» °¡Áö°í ÀÖÀ¸³ª, ±âÁ¸ µ¥ÀÌÅͼ°ú ¸¶ÀÌÅÍ ¾îÅà ¶óº§ °£ÀÇ º¯È¯ ½Ã ¿Ïº®ÇÏ°Ô ÀÏÄ¡ÇÒ ¼ö ¾ø´Â Á¡°ú Áö³ªÄ£ Èñ¼Ò Ŭ·¡½º Á¸Àç·Î ÀÎÇÑ ÇÑ°è°¡ ÀÖÀ½À» ÀÎÁöÇÏ¿´´Ù. ±×·³¿¡µµ ºÒ±¸ÇÏ°í B-SMOTE¸¦ Àû¿ëÇÑ Catboost´Â 0.9526ÀÇ ºÐ·ù Á¤È®µµ¸¦ ´Þ¼ºÇÏ¿´°í ÀÌ´Â Á¤»ó/ºñÁ¤»ó ³×Æ®¿öÅ© Æ®·¡ÇÈÀ» ÀÚµ¿À¸·Î ŽÁöÇÒ ¼ö ÀÖÀ» °ÍÀ¸·Î º¸ÀδÙ.
¿µ¹®³»¿ë
(English Abstract)
This study proposed a classification of malicious network traffic using the cyber threat framework(Mitre ATT&CK) and machine learning to solve the real-time traffic detection problems faced by current security monitoring systems. We applied a network traffic dataset called UNSW-NB15 to the Mitre ATT&CK framework to transform the label and generate the final dataset through rare class processing. After learning several boosting-based ensemble models using the generated final dataset, we demonstrated how these ensemble models classify network traffic using various performance metrics. Based on the F-1 score, we showed that XGBoost with no rare class processing is the best in the multi-class traffic environment. We recognized that machine learning ensemble models through Mitre ATT&CK label conversion and oversampling processing have differences over existing studies, but have limitations due to (1) the inability to match perfectly when converting between existing datasets and Mitre ATT&CK labels and (2) the presence of excessive sparse classes. Nevertheless, Catboost with B-SMOTE achieved the classification accuracy of 0.9526, which is expected to be able to automatically detect normal/abnormal network traffic.
Å°¿öµå(Keyword) ¸Ó½Å·¯´×   ¸¶ÀÌÅÍ ¾îÅà  UNSW-NB15   ³×Æ®¿öÅ© Æ®·¡ÇÈ ºÐ·ù   ³×Æ®¿öÅ© º¸¾È °üÁ¦   Machine Learning   Mitre ATT&CK   UNSW-NB15   Network Traffic Classification   Network Security Monitoring  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå