• 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»êÈ­ Àüó¸® ¹æ½Ä ¹× ÄÁº¼·ç¼Ç ½Å°æ¸ÁÀ» È°¿ëÇÑ ³×Æ®¿öÅ© ħÀÔ Å½Áö¿¡ ´ëÇÑ ¿¬±¸
¿µ¹®Á¦¸ñ(English Title) A Research on Network Intrusion Detection based on Discrete Preprocessing Method and Convolution Neural Network
ÀúÀÚ(Author) À¯ÁöÈÆ   ¹Îº´ÁØ   ±è»ó¼ö   ½Åµ¿ÀÏ   ½Åµ¿±Ô   iHoon Yoo   Byeongjun Min   Sangsoo Kim   Dongil Shin   Dongkyoo Shin  
¿ø¹®¼ö·Ïó(Citation) VOL 22 NO. 02 PP. 0029 ~ 0039 (2021. 04)
Çѱ۳»¿ë
(Korean Abstract)
»õ·Ó°Ô ¹ß»ýµÇ´Â »çÀ̹ö °ø°ÝÀ¸·Î ÀÎÇØ °³ÀÎ, ¹Î°£ ¹× ±â¾÷ÀÇ ÇÇÇØ°¡ Áõ°¡ÇÔ¿¡ µû¶ó, ÀÌ¿¡ ±â¹ÝÀÌ µÇ´Â ³×Æ®¿öÅ© º¸¾È ¹®Á¦´Â ÄÄÇ»ÅÍ ½Ã½ºÅÛÀÇ ÁÖ¿ä ¹®Á¦·Î ºÎ°¢µÇ¾ú´Ù. ÀÌ¿¡ ±âÁ¸¿¡ »ç¿ëµÇ´Â ³×Æ®¿öÅ© ħÀÔ Å½Áö ½Ã½ºÅÛ(Network Intrusion Detection System: NIDS)¿¡¼­ ¹ß»ýµÇ´Â ÇÑ°èÁ¡À» °³¼±ÇÏ°íÀÚ ±â°è ÇнÀ°ú µö·¯´×À» È°¿ëÇÑ ¿¬±¸ ÀÌ·ïÁö°í ÀÖ´Ù. ÀÌ¿¡ º» ¿¬±¸¿¡¼­´Â CNN(Convolution Neural Network) ¾Ë°í¸®ÁòÀ» ÀÌ¿ëÇÑ NIDS ¸ðµ¨ ¿¬±¸¸¦ ÁøÇàÇÑ´Ù. À̹ÌÁö ºÐ·ù ±â¹ÝÀÇ CNN ¾Ë°í¸®Áò ÇнÀÀ» À§ÇØ ±âÁ¸ »ç¿ëµÇ´Â Àüó¸® ´Ü°è¿¡¼­ ¿¬¼Ó¼º º¯¼ö ÀÌ»êÈ­(Discretization of Continuous) ¾Ë°í¸®ÁòÀ» Ãß°¡ÇÏ¿© ¿¹Ãø º¯¼ö¿¡ ´ëÇØ ¼±Çü °ü°è·Î Ç¥ÇöÇÏ¿© Çؼ®¿¡ ¿ëÀÌÇÑ µ¥ÀÌÅÍ·Î º¯È¯ ÈÄ, Á¤»ç°¢Çü Çà·Ä(Square Matrix) ±¸Á¶¿¡ ¸ÅĪµÈ Çȼ¿(Pixel) À̹ÌÁö ±¸Á¶¸¦ ¸ðµ¨¿¡ ÇнÀÇÑ´Ù. ¸ðµ¨ÀÇ ¼º´É Æò°¡¸¦ À§ÇØ ³×Æ®¿öÅ© ÆÐŶ µ¥ÀÌÅÍÀÎ NSL-KDD¸¦ »ç¿ëÇÏ¿´À¸¸ç, Á¤È®µµ(Accuracy), Á¤¹Ðµµ(Precision), ÀçÇöÀ²(Recall) ¹× Á¶È­Æò±Õ(F1-score)À» ¼º´É ÁöÇ¥·Î »ç¿ëÇÏ¿´´Ù. ½ÇÇè °á°ú Á¦¾ÈµÈ ¸ðµ¨¿¡¼­ 85%ÀÇ Á¤È®µµ·Î °¡Àå ³ôÀº ¼º´ÉÀ» º¸¿´À¸¸ç, ÇнÀ Ç¥º»ÀÌ ÀûÀº R2L Ŭ·¡½ºÀÇ Á¶È­Æò±ÕÀÌ 71% ¼º´ÉÀ¸·Î ´Ù¸¥ ¸ðµ¨¿¡ ºñÇؼ­ ¸Å¿ì ÁÁÀº ¼º´ÉÀ» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
As damages to individuals, private sectors, and businesses increase due to newly occurring cyber attacks, the underlying network security problem has emerged as a major problem in computer systems. Therefore, NIDS using machine learning and deep learning is being studied to improve the limitations that occur in the existing Network Intrusion Detection System. In this study, a deep learning-based NIDS model study is conducted using the Convolution Neural Network (CNN) algorithm. For the image classification-based CNN algorithm learning, a discrete algorithm for continuity variables was added in the preprocessing stage used previously, and the predicted variables were expressed in a linear relationship and converted into easy-to-interpret data. Finally, the network packet processed through the above process is mapped to a square matrix structure and converted into a pixel image. For the performance evaluation of the proposed model, NSL-KDD, a representative network packet data, was used, and accuracy, precision, recall, and f1-score were used as performance indicators. As a result of the experiment, the proposed model showed the highest performance with an accuracy of 85%, and the harmonic mean (F1-Score) of the R2L class with a small number of trainingsamples was 71%, showing very good performance compared to other models.
Å°¿öµå(Keyword) NSL-KDD   ³×Æ®¿öÅ© ÀÌ»ó ŽÁö   CNN   ¿¬¼ÓÇü º¯¼ö ÀÌ»êÇüÈ­   NSL-KDD   Network Intrusion Detection   CNN   Discretization of Continuous  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå