• 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) ±º Æó¼â¸Á ȯ°æ¿¡¼­ÀÇ ¸ðÀÇ ³×Æ®¿öÅ© µ¥ÀÌÅÍ ¼Â Æò°¡ ¹æ¹ý ¿¬±¸
¿µ¹®Á¦¸ñ(English Title) A study on evaluation method of NIDS datasets in closed military network
ÀúÀÚ(Author) ¹Ú¿ëºó   ½Å¼º¿í   ÀÌÀμ·   Yong-bin Park   Sung-uk Shin   In-sup Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 21 NO. 02 PP. 0121 ~ 0130 (2020. 04)
Çѱ۳»¿ë
(Korean Abstract)
ÀÌ ³í¹®Àº Generative Adversarial Network (GAN) À» ÀÌ¿ëÇÏ¿© ÁõÁøµÈ À̹ÌÁö µ¥ÀÌÅ͸¦ Æò°¡¹æ½ÄÀÎ Inception Score (IS) ¿Í Frechet Inception Distance (FID) °è»ê½Ã inceptionV3 ¸ðµ¨À» È°¿ë ÇÏ´Â ¹æ½ÄÀ» ÀÀ¿ëÇÏ¿©, ±º Æó¼â¸Á ³×Æ®¿öÅ© µ¥ÀÌÅ͸¦ À̹ÌÁö ÇüÅ·ΠÆò°¡ÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. ±âÁ¸ Á¸ÀçÇÏ´Â À̹ÌÁö ºÐ·ù ¸ðµ¨µé¿¡ ·¹À̾ Ãß°¡ÇÏ¿© IncetptionV3 ¸ðµ¨À» ´ëüÇÏ°í, ³×Æ®¿öÅ© µ¥ÀÌÅ͸¦ À̹ÌÁö·Î º¯È¯ ¹× ÇнÀ ÇÏ´Â ¹æ¹ý¿¡ º¯È­¸¦ ÁÖ¾î ´Ù¾çÇÑ ½Ã¹Ä·¹À̼ÇÀ» ÁøÇàÇÏ¿´´Ù. ½ÇÇè °á°ú, atanÀ» ÀÌ¿ëÇØ 8 * 8 À̹ÌÁö·Î º¯È¯ÇÑ µ¥ÀÌÅÍ¿¡ ´ëÇØ 1°³ÀÇ µ§½º ·¹À̾î (Dense Layer)¸¦ Ãß°¡ÇÑ Densenet121¸¦ ÇнÀ½ÃŲ ¸ðµ¨ÀÌ ³×Æ®¿öÅ© µ¥ÀÌÅͼ Æò°¡ ¸ðµ¨·Î¼­ °¡Àå ÀûÇÕÇÏ´Ù´Â °á°ú¸¦ µµÃâÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
This paper suggests evaluating the military closed network data as an image which is generated by Generative Adversarial Network (GAN), applying an image evaluation method such as the InceptionV3 model-based Inception Score (IS) and Frechet Inception Distance (FID). We employed the famous image classification models instead of the InceptionV3, added layers to those models, and converted the network data to an image in diverse ways. Experimental results show that the Densenet121 model with one added Dense Layer achieves the best performance in data converted using the arctangent algorithm and 8 * 8 size of the image.
Å°¿öµå(Keyword) µ¥ÀÌÅÍ ¼Â   ³×Æ®¿öÅ© ħÀÔ Å½Áö ½Ã½ºÅÛ   ¸Ó½Å·¯´×   dataset   Machine Learning   Network Intrusion Detection System   µ¥ÀÌÅÍ Æò°¡   Data evaluation  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå