• 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 : 593 / 594

ÇѱÛÁ¦¸ñ(Korean Title) ¿£Æ®·ÎÇÇ ½Ã°è¿­ µ¥ÀÌÅÍ ÃßÃâ°ú ¼øȯ ½Å°æ¸ÁÀ» ÀÌ¿ëÇÑ IoT ¾Ç¼ºÄÚµå ŽÁö¿Í Æйи® ºÐ·ù
¿µ¹®Á¦¸ñ(English Title) IoT Malware Detection and Family Classification Using Entropy Time Series Data Extraction and Recurrent Neural Networks
ÀúÀÚ(Author) ±è¿µÈ£   ÀÌÇöÁ¾   ȲµÎ¼º   Youngho Kim   Hyunjong Lee   Doosung Hwang  
¿ø¹®¼ö·Ïó(Citation) VOL 11 NO. 05 PP. 0197 ~ 0202 (2022. 05)
Çѱ۳»¿ë
(Korean Abstract)
IoT (Internet of Things) ÀåÄ¡´Â Ãë¾àÇÑ ¾ÆÀ̵ð/ºñ¹Ð¹øÈ£ »ç¿ë, ÀÎÁõµÇÁö ¾ÊÀº Æß¿þ¾î ¾÷µ¥ÀÌÆ® µî ¸¹Àº º¸¾È Ãë¾àÁ¡À» º¸¿© ¾Ç¼ºÄÚµåÀÇ °ø°Ý ´ë»óÀÌ µÇ°í ÀÖ´Ù. ±×·¯³ª CPU ±¸Á¶ÀÇ ´Ù¾ç¼ºÀ¸·Î ÀÎÇØ ¾Ç¼ºÄÚµå ºÐ¼® ȯ°æ ¼³Á¤°ú Ư¡ ¼³°è¿¡ ¾î·Á¿òÀÌ ÀÖ´Ù. º» ³í¹®¿¡¼­´Â CPU ±¸Á¶¿Í µ¶¸³µÈ ¾Ç¼ºÄÚµåÀÇ Æ¯Â¡ Ç¥ÇöÀ» À§ÇØ ½ÇÇà ÆÄÀÏÀÇ ¹ÙÀÌÆ® ¼ø¼­¸¦ ÀÌ¿ëÇÑ ½Ã°è¿­ Ư¡À» ¼³°èÇÏ°í ¼øȯ ½Å°æ¸ÁÀ» ÅëÇØ ºÐ¼®ÇÑ´Ù. Á¦¾ÈÇϴ Ư¡Àº ¹ÙÀÌÆ® ¼ø¼­ÀÇ ºÎºÐ ¿£Æ®·ÎÇÇ °è»ê°ú ¼±Çü º¸°£À» ÅëÇÑ °íÁ¤ ±æÀÌÀÇ ½Ã°è¿­ ÆÐÅÏÀÌ´Ù. ÃßÃâµÈ Ư¡ÀÇ ½Ã°è¿­ º¯È­´Â RNN°ú LSTMÀ¸·Î ÇнÀ½ÃÄÑ ºÐ¼®ÇÑ´Ù. ½ÇÇè¿¡¼­ IoT ¾Ç¼ºÄÚµå ŽÁö´Â ³ôÀº ¼º´ÉÀ» º¸¿´Áö¸¸, Æйи® ºÐ·ù´Â ºñ±³Àû ¼º´ÉÀÌ ³·¾Ò´Ù. ¾Ç¼ºÄÚµå Æйи®º° ¿£Æ®·ÎÇÇ ÆÐÅÏÀ» ½Ã°¢È­ÇÏ¿© ºñ±³ÇßÀ» ¶§ Tsunami¿Í Gafgyt Æйи®°¡ À¯»çÇÑ ÆÐÅÏÀ» ³ªÅ¸³» ºÐ·ù ¼º´ÉÀÌ ³·¾ÆÁø °ÍÀ¸·Î ºÐ¼®µÇ¾ú´Ù. Á¦¾ÈµÈ ¾Ç¼ºÄÚµå Ư¡ÀÇ µ¥ÀÌÅÍ °£ ½Ã°è¿­ º¯È­ ÇнÀ¿¡ RNNº¸´Ù LSTMÀÌ ´õ ÀûÇÕÇÏ´Ù.
¿µ¹®³»¿ë
(English Abstract)
IoT (Internet of Things) devices are being attacked by malware due to many security vulnerabilities, such as the use of weak IDs/passwords and unauthenticated firmware updates. However, due to the diversity of CPU architectures, it is difficult to set up a malware analysis environment and design features. In this paper, we design time series features using the byte sequence of executable files to represent independent features of CPU architectures, and analyze them using recurrent neural networks. The proposed feature is a fixed-length time series pattern extracted from the byte sequence by calculating partial entropy and applying linear interpolation. Temporary changes in the extracted feature are analyzed by RNN and LSTM. In the experiment, the IoT malware detection showed high performance, while low performance was analyzed in the malware family classification. When the entropy patterns for each malware family were compared visually, the Tsunami and Gafgyt families showed similar patterns, resulting in low performance. LSTM is more suitable than RNN for learning temporal changes in the proposed malware features.
Å°¿öµå(Keyword) »ç¹° ÀÎÅͳݠ  ±â°èÇнÀ   ¾Ç¼ºÄÚµå ŽÁö   ¾Ç¼ºÄÚµå Æйи® ºÐ·ù   Internet of Things   Machine Learning   Malware Detection   Malware Family Classification  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå