Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
Áߺ¹ Çã¿ë ¹üÀ§¸¦ °í·ÁÇÑ ¼¹ÙÀ̹ú ³×Æ®¿öÅ© ±â¹Ý ¾Èµå·ÎÀ̵å ÀúÀÚ ½Äº° |
¿µ¹®Á¦¸ñ(English Title) |
Survival network based Android Authorship Attribution considering overlapping tolerance |
ÀúÀÚ(Author) |
Jaehong Min
Sunggeun Han
Bu-young Ahn
ȲöÈÆ
½Å°ÇÀ±
±èµ¿¿í
ÇÑ¸í¹¬
Cheol-hun Hwang
Gun-Yoon Shin
Dong-Wook Kim
Myung-Mook Han
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 21 NO. 06 PP. 0013 ~ 0021 (2020. 12) |
Çѱ۳»¿ë (Korean Abstract) |
¾Èµå·ÎÀ̵å ÀúÀÚ ½Äº° ¿¬±¸´Â Á¼Àº ¹üÀ§¿¡¼´Â Ãâó¸¦ ¹àÈ÷±â À§ÇÑ ¹æ¹ýÀ¸·Î Çؼ®ÇÒ ¼ö ÀÖÀ¸³ª, ³ÐÀº ¹üÀ§¿¡¼ º»´Ù¸é ¾Ë·ÁÁø ÀúÀÛ¹°À» ÅëÇØ À¯»çÇÑ ÀúÀÛ¹°À» ½Äº°ÇÏ´Â ÅëÂû·ÂÀ» ¾ò±â À§ÇÑ ¹æ¹ýÀ¸·Î Çؼ®ÇÒ ¼ö ÀÖ´Ù. ¾Èµå·ÎÀ̵å ÀúÀÚ ½Äº° ¿¬±¸¿¡¼ ¹ß°ßµÇ´Â ¹®Á¦Á¡Àº ¾Èµå·ÎÀÌµå ½Ã½ºÅÛ »ó Áß¿äÇÑ ÄÚµåÀÌÁö¸¸ Àǹ̰¡ ¾ø´Â ÄÚµåµé·Î ÀÎÇÏ¿© ÀúÀÚÀÇ Áß¿äÇÑ Æ¯Â¡À» ã±â ¾î·Æ´Ù´Â °ÍÀÌ´Ù. ÀÌ·Î ÀÎÇØ ÇÕ¹ýÀûÀÎ ÄÚµå ¶Ç´Â ÇൿµéÀÌ ¾Ç¼ºÄÚµå·Î À߸ø Á¤ÀǵDZ⵵ ÇÑ´Ù. À̸¦ ÇØ°áÇϱâ À§ÇÏ¿© ¼¹ÙÀ̹ú ³×Æ®¿öÅ© °³³äÀ» µµÀÔÇÏ¿© ¿©·¯ ¾Èµå·ÎÀÌµå ¾Û¿¡¼ ¹ß°ßµÇ´Â Ư¡µéÀ» Á¦°ÅÇÏ°í ÀúÀÚº°·Î Á¤ÀǵǴ °íÀ¯ÇÑ Æ¯Â¡µéÀ» »ýÁ¸½ÃÅ´À¸·Î½á ¹®Á¦¸¦ ÇØ°áÇÏ°íÀÚ ÇÏ¿´´Ù. Á¦¾ÈÇÏ´Â ÇÁ·¹ÀÓ¿öÅ©¿Í ¼±ÇàµÈ ¿¬±¸¸¦ ºñ±³ÇÏ´Â ½ÇÇèÀ» ÁøÇàÇÏ¿´À¸¸ç, 440°³ÀÇ ÀúÀÚ°¡ ½Äº°µÈ ¾ÛÀ» ´ë»óÀ¸·Î ½ÇÇèÇÑ °á°ú¿¡¼ ÃÖ´ë 92.10%ÀÇ ºÐ·ù Á¤È®µµ¸¦ µµÃâÇÏ¿´°í ¼±ÇàµÈ ¿¬±¸¿Í ÃÖ´ë 3.47%ÀÇ Â÷À̸¦ º¸¿´´Ù. ÀÌ´Â ÀûÀº ¾çÀÇ ÇнÀµ¥ÀÌÅ͸¦ ÀÌ¿ëÇÏ¿´À¸³ª ÀúÀÚº° Áߺ¹µÈ Ư¡ ¾øÀÌ °íÀ¯ÇÑ Æ¯Â¡µéÀ» ÀÌ¿ëÇÏ¿´±â¿¡ ¼±Çà ¿¬±¸¿Í Â÷ÀÌ°¡ ³ªÅ¸³µÀ» °ÍÀ¸·Î Çؼ®ÇÏ¿´´Ù. ¶ÇÇÑ Æ¯Â¡ Á¤ÀÇ ¹æ¹ý¿¡ µû¸¥ ¼±Çà ¿¬±¸¿ÍÀÇ ºñ±³ ½ÇÇè¿¡¼µµ ÀûÀº ¼öÀÇ Æ¯Â¡À¸·Î µ¿ÀÏÇÑ Á¤È®µµ¸¦ º¸ÀÏ ¼ö ÀÖÀ¸¸ç, ÀÌ´Â ¼¹ÙÀ̹ú ³×Æ®¿öÅ© °³³äÀ» ÅëÇÑ Áö¼ÓÀûÀ¸·Î Áߺ¹µÈ ÀÇ¹Ì ¾ø´Â Ư¡À» °ü¸®ÇÒ ¼ö ÀÖÀ½À» ¾Ë ¼ö ÀÖ¾ú´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
The Android author identification study can be interpreted as a method for revealing the source in a narrow range, but if viewed in a wide range, it can be interpreted as a study to gain insight to identify similar works through known works. The problem found in the Android author identification study is that it is an important code on the Android system, but it is difficult to find the important feature of the author due to the meaningless codes. Due to this, legitimate codes or behaviors were also incorrectly defined as malicious codes. To solve this, we introduced the concept of survival network to solve the problem by removing the features found in various Android apps and surviving unique features defined by authors. We conducted an experiment comparing the proposed framework with a previous study. From the results of experiments on 440 authors' identified apps, we obtained a classification accuracy of up to 92.10%, and showed a difference of up to 3.47% from the previous study. It used a small amount of learning data, but because it used unique features without duplicate features for each author, it was considered that there was a difference from previous studies. In addition, even in comparative experiments with previous studies according to the feature definition method, the same accuracy can be shown with a small number of features, and this can be seen that continuously overlapping meaningless features can be managed through the concept of a survival network.
|
Å°¿öµå(Keyword) |
Data education
trainee
educational trends
Data usage and analysis
data
¾Èµå·ÎÀ̵å ÀúÀÚ ½Äº°
ÀúÀÚ ½Äº°
Áߺ¹ Ư¡ Á¦°Å
¼¹ÙÀ̹ú ³×Æ®¿öÅ©
Android Authorship Attribution
Authorship Attribution
Remove duplicate features
Survival network
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|