• 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 :

ÇѱÛÁ¦¸ñ(Korean Title) ´Ù¾çÇÑ µ¥ÀÌÅÍ Àüó¸® ±â¹ý ±â¹Ý ħÀÔŽÁö ½Ã½ºÅÛÀÇ ÀÌ»óŽÁö Á¤È®µµ ºñ±³ ¿¬±¸
¿µ¹®Á¦¸ñ(English Title) Comparative Study of Anomaly Detection Accuracy of Intrusion Detection Systems Based on Various Data Preprocessing Techniques
ÀúÀÚ(Author) ¹Ú°æ¼±   ±è°­¼®   Kyungseon Park   Kangseok Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 10 NO. 11 PP. 0449 ~ 0456 (2021. 11)
Çѱ۳»¿ë
(Korean Abstract)
ħÀÔ Å½Áö ½Ã½ºÅÛ(IDS: Intrusion Detection System)Àº º¸¾ÈÀ» ħÇØÇÏ´Â ÀÌ»ó ÇàÀ§¸¦ ŽÁöÇÏ´Â ±â¼ú·Î¼­ ºñÁ¤»óÀûÀÎ Á¶ÀÛÀ» ŽÁöÇÏ°í ½Ã½ºÅÛ °ø°ÝÀ» ¹æÁöÇÑ´Ù. ±âÁ¸ÀÇ Ä§ÀÔŽÁö ½Ã½ºÅÛÀº Æ®·¡ÇÈ ÆÐÅÏÀ» Åë°è ±â¹ÝÀ¸·Î ºÐ¼®ÇÏ¿© ¼³°èÇÏ¿´´Ù. ±×·¯³ª ±Þ¼Óµµ·Î ¼ºÀåÇÏ´Â ±â¼ú¿¡ ÀÇÇØ Çö´ëÀÇ ½Ã½ºÅÛÀº ´Ù¾çÇÑ Æ®·¡ÇÈÀ» »ý¼ºÇϱ⠶§¹®¿¡ ±âÁ¸ÀÇ ¹æ¹ýÀº ÇÑ°èÁ¡ÀÌ ¸íÈ®ÇØÁ³´Ù. ÀÌ·± ÇÑ°èÁ¡À» ±Øº¹Çϱâ À§ÇØ ´Ù¾çÇÑ ±â°èÇнÀ ±â¹ýÀ» Àû¿ëÇÑ Ä§ÀÔŽÁö ¹æ¹ýÀÇ ¿¬±¸°¡ È°¹ßÈ÷ ÁøÇàµÇ°í ÀÖ´Ù. º» ³í¹®¿¡¼­´Â ´Ù¾çÇÑ ³×Æ®¿öÅ© ȯ°æÀÇ Æ®·¡ÇÈÀ» ½Ã¹Ä·¹ÀÌ¼Ç Àåºñ¿¡¼­ »ý¼ºÇÑ NGIDS-DS(Next Generation IDS Dataset)¸¦ ÀÌ¿ëÇÏ¿© ÀÌ»ó(Anomaly) ŽÁö Á¤È®µµ¸¦ ³ôÀÏ ¼ö ÀÖ´Â µ¥ÀÌÅÍ Àüó¸® ±â¹ý¿¡ °üÇÑ ºñ±³ ¿¬±¸¸¦ ÁøÇàÇÏ¿´´Ù. µ¥ÀÌÅÍ Àü󸮷ΠÆеù(Padding)°ú ½½¶óÀ̵ù À©µµ¿ì(Sliding Window)¸¦ »ç¿ëÇÏ¿´°í, Á¤»ó µ¥ÀÌÅÍ ºñÀ²°ú ÀÌ»ó µ¥ÀÌÅÍ ºñÀ²ÀÇ ºÒ±ÕÇü ¹®Á¦¸¦ ÇØ°áÇϱâ À§ÇØ AAE(Adversarial Auto-Encoder)¸¦ Àû¿ëÇÑ ¿À¹ö»ùÇøµ ±â¹ý µîÀ» Àû¿ëÇÏ¿´´Ù. ¶ÇÇÑ, Àüó¸®µÈ ½ÃÄö½º µ¥ÀÌÅÍÀÇ Æ¯Â¡º¤Å͸¦ ÃßÃâÇÒ ¼ö ÀÖ´Â Word2Vec ±â¹ý Áß Skip-gramÀ» ÀÌ¿ëÇÏ¿© ŽÁö Á¤È®µµÀÇ ¼º´É Çâ»óÀ» È®ÀÎÇÏ¿´´Ù. ºñ±³½ÇÇèÀ» À§ÇÑ ¸ðµ¨·Î´Â PCA-SVM°ú GRU¸¦ »ç¿ëÇÏ¿´°í, ½ÇÇè °á°ú´Â ½½¶óÀ̵ù À©µµ¿ì, Skip-gram, AAE, GRU¸¦ Àû¿ëÇÏ¿´À» ¶§, ´õ ÁÁÀº ¼º´ÉÀ» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
An intrusion detection system is a technology that detects abnormal behaviors that violate security, and detects abnormal operations and prevents system attacks. Existing intrusion detection systems have been designed using statistical analysis or anomaly detection techniques for traffic patterns, but modern systems generate a variety of traffic different from existing systems due to rapidly growing technologies, so the existing methods have limitations. In order to overcome this limitation, study on intrusion detection methods applying various machine learning techniques is being actively conducted. In this study, a comparative study was conducted on data preprocessing techniques that can improve the accuracy of anomaly detection using NGIDS-DS (Next Generation IDS Database) generated by simulation equipment for traffic in various network environments. Padding and sliding window were used as data preprocessing, and an oversampling technique with Adversarial Auto-Encoder (AAE) was applied to solve the problem of imbalance between the normal data rate and the abnormal data rate. In addition, the performance improvement of detection accuracy was confirmed by using Skip-gram among the Word2Vec techniques that can extract feature vectors of preprocessed sequence data. PCA-SVM and GRU were used as models for comparative experiments, and the experimental results showed better performance when sliding window, skip-gram, AAE, and GRU were applied.
Å°¿öµå(Keyword) ħÀÔŽÁö   ½½¶óÀ̵ù À©µµ¿ì   Skip-gram   AAE   GRU   Intrusion Detection   Sliding Window   Skip-gram   AAE   GRU  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå