• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ÇÐȸÁö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ÇÐȸÁö > µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)

µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ½ÉÃþ½Å°æ¸Á¿¡¼­ ÇнÀ ¿Ü ºÐÆ÷ µ¥ÀÌÅÍ Å½Áö ¾Ë°í¸®Áò
¿µ¹®Á¦¸ñ(English Title) Detecting Out-of-distribution data for Deep Neural Networks
ÀúÀÚ(Author) ±è»ó¿ø   ÀÌÈ£ÁØ   ±è¼ºÈÆ   ¼­Áö¿ø   Sangwon Kim   Hojun Lee   Seonghun Kim   Jiwon Seo  
¿ø¹®¼ö·Ïó(Citation) VOL 35 NO. 02 PP. 0066 ~ 0077 (2019. 08)
Çѱ۳»¿ë
(Korean Abstract)
½ÉÃþ½Å°æ¸Á ȤÀº ¿¡¼­ÀÇ ÇнÀ ¿Ü ºÐÆ÷ µ¥ÀÌÅÍ (Deep Neural Network, DNN) (Out-of-Distribution Data)¶õ ÇØ´ç ½ÉÃþ½Å°æ¸ÁÀ» ÇнÀ½ÃŲ µ¥ÀÌÅÍ¿Í »ó´çÇÑ Â÷À̸¦ º¸ÀÌ´Â µ¥ÀÌÅ͸¦ ¸»ÇÑ´Ù. ÇÏÁö¸¸, ½ÉÃþ½Å°æ¸ÁÀÌ µµÃâÇÏ´Â °á°ú¿¡ ´ëÇÑ ±Ù°Å¿Í µµÃâ ¹æ¹ýÀ» ÀÌÇØÇÏ´Â °ÍÀÌ ¾î·Æ±â ¶§¹®¿¡ ÇнÀ ¿Ü ºÐÆ÷ µ¥ÀÌÅ͸¦ ŽÁöÇϱ⠾î·Æ´Ù. º» ³í¹®¿¡¼­´Â ¸¹Àº µ¥ÀÌÅÍµé ¼Ó¿¡¼­ ±×·¯ÇÑ ÇнÀ ¿Ü ºÐÆ÷ µ¥ÀÌÅ͸¦ Á¤È®ÇÏ°Ô ½Äº°Çϱâ À§ÇØ µ¶Ã¢ÀûÀÎ ±â¹ýÀ» Á¦¾ÈÇÑ´Ù ÀÌ ±â¹ýÀº ÇнÀ ³» ºÐÆ÷ µ¥ÀÌÅÍ¿¡ ´ëÀÀÇÏ´Â Àº´Ð ´º·ÐµéÀÌ Æ¯Á¤ÇÑ ºÐÆ÷¸¦ °¡Áø´Ù´Â °¡Á¤À» ±â¹ÝÀ¸·Î ÇÑ´Ù. ÀÌ·¯ÇÑ, °¡Á¤ ÇÏ¿¡¼­ º» ±â¹ýÀº ÇнÀ ³» ºÐÆ÷ µ¥ÀÌÅ͸¦ ºñ½ÁÇÑ Àº´Ð ´º·Ð ÆÐÅÏÀ» °¡Áø °Í³¢¸® ±ºÁýÈ­ ÇÑ ÈÄ ±× °á°ú¸¦ ¹ÙÅÁÀ¸·Î ÇнÀ ¿Ü ºÐÆ÷ µ¥ÀÌÅ͸¦ °ËÃâÇÑ´Ù
¿µ¹®³»¿ë
(English Abstract)
The inference outcome of a Deep Neural Network (DNN) may be incorrect if the input is substantially different from the distribution of its training data. Thus detecting such out-of-distribution (OOD) data is essential for a DNN to be securely applied. Because we do not yet understand why and how a DNN makes an inference, it is hard to identify OOD data by examining the inference process. We propose a novel method to accurately detect OOD data and in-distribution (ID) data. Our method assumes that there exists a specific distribution of the values of hidden neurons for ID data. Under this assumption, our method clusters ID data with similar hidden-neuron patterns and detect OOD data based on the clustering results.
Å°¿öµå(Keyword) Deep Neural Network   Out-of-Distribution detection   Deep Neural Network Security   ½ÉÃþ½Å°æ¸Á ÇнÀ   ºÐÆ÷ µ¥ÀÌÅÍ Å½Áö   ½ÉÃþ½Å°æ¸Á º¸¾È  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå