Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ÄÄÇ»ÅÍ ¹× Åë½Å½Ã½ºÅÛ
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
k-À͸íÈ ¾Ë°í¸®Áò¿¡¼ ±â°èÇнÀ ±â¹ÝÀÇ k°ª ¿¹Ãø ±â¹ý ½ÇÇè ¹× ±¸Çö |
¿µ¹®Á¦¸ñ(English Title) |
Experiment and Implementation of a Machine-Learning Based k-Value Prediction Scheme in a k-Anonymity Algorithm |
ÀúÀÚ(Author) |
À强ºÀ
Kumbayoni Lalu Muh
Sung-Bong Jang
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 09 NO. 01 PP. 0009 ~ 0016 (2020. 01) |
Çѱ۳»¿ë (Korean Abstract) |
ºò µ¥ÀÌÅ͸¦ ¿¬±¸ ¸ñÀûÀ¸·Î Á¦3ÀÚ¿¡°Ô ¹èÆ÷ÇÒ ¶§ ÇÁ¶óÀ̹ö½Ã Á¤º¸¸¦ º¸È£Çϱâ À§Çؼ k-À͸íÈ ±â¹ýÀÌ ³Î¸® »ç¿ëµÇ¾î ¿Ô´Ù. k-À͸íÈ ±â¹ýÀ» Àû¿ëÇÒ ¶§, ÇØ°á ÇؾßÇÒ ¾î·Á¿î ¹®Á¦ ÁßÀÇ Çϳª´Â ÃÖÀûÀÇ k°ªÀ» °áÁ¤ÇÏ´Â °ÍÀÌ´Ù. ÇöÀç´Â ´ëºÎºÐ Àü¹®°¡ÀÇ Á÷°ü¿¡ ±Ù°ÅÇÏ¿© ¼öµ¿À¸·Î °áÁ¤µÇ°í ÀÖ´Ù. ÀÌ·¯ÇÑ ¹æ½ÄÀº À͸íÈÀÇ ¼º´ÉÀ» ¶³¾î¶ß¸®°í ½Ã°£°ú ºñ¿ëÀ» ¸¹ÀÌ ³¶ºñÇÏ°Ô ¸¸µç´Ù. ÀÌ·¯ÇÑ ¹®Á¦Á¡À» ÇØ°áÇϱâ À§Çؼ ±â°èÇнÀ ±â¹ÝÀÇ k°ª °áÁ¤¹æ½ÄÀ» Á¦¾ÈÇÑ´Ù. º» ³í¹®¿¡¼´Â Á¦¾ÈµÈ ¾ÆÀ̵ð¾î¸¦ ½ÇÁ¦·Î Àû¿ëÇÑ ±¸Çö ¹× ½ÇÇè ³»¿ë¿¡ ´ëÇؼ ¼¼ú ÇÑ´Ù. ½ÇÇè¿¡¼´Â ½ÉÃþ ½Å°æ¸ÁÀ» ±¸ÇöÇÏ¿© ÈÆ·ÃÇÏ°í Å×½ºÆ®¸¦ ¼öÇà ÇÏ¿´´Ù. ½ÇÇè°á°ú ÈÆ·Ã ¿¡·¯´Â ÀüÇüÀûÀÎ ½Å°æ¸Á¿¡¼ º¸¿©Áö´Â ÆÐÅÏÀ» ³ªÅ¸³ÂÀ¸¸ç, Å×½ºÆ® ½ÇÇè¿¡¼´Â ÈƷÿ¡·¯¿¡¼ ³ªÅ¸³ª´Â ÆÐÅÏ°ú´Â ´Ù¸¥ ÆÐÅÏÀ» º¸¿©ÁÖ°í ÀÖ´Ù. Á¦¾ÈµÈ ¹æ½ÄÀÇ ÀåÁ¡Àº k°ª °áÁ¤½Ã ½Ã°£°ú ºñ¿ëÀ» ÁÙÀÏ ¼ö ÀÖ´Ù´Â ÀåÁ¡ÀÌ ÀÖ´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
The k-anonymity scheme has been widely used to protect private information when Big Data are distributed to a third party for research purposes. When the scheme is applied, an optimal k value determination is one of difficult problems to be resolved because many factors should be considered. Currently, the determination has been done almost manually by human experts with their intuition. This leads to degrade performance of the anonymization, and it takes much time and cost for them to do a task. To overcome this problem, a simple idea has been proposed that is based on machine learning. This paper describes implementations and experiments to realize the proposed idea. In thi work, a deep neural network (DNN) is implemented using tensorflow libraries, and it is trained and tested using input dataset. The experiment results show that a trend of training errors follows a typical pattern in DNN, but for validation errors, our model represents a different pattern from one shown in typical training process. The advantage of the proposed approach is that it can reduce time and cost for experts to determine k value because it can be done semi-automatically.
|
Å°¿öµå(Keyword) |
Àΰø ½Å°æ¸Á
k-À͸íÈ
k°ª ¿¹Ãø
ÅÙ¼Ç÷οì
Artificial Neural Networks
k-Anonymity
k Value Prediction
TensorFlow
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|