Àüü
ÀüÀÚ/Àü±â
Åë½Å
ÄÄÇ»ÅÍ
·Î±×ÀÎ
ȸ¿ø°¡ÀÔ
About Us
ÀÌ¿ë¾È³»
¿¬±¸¹®Çå
±¹³» ³í¹®Áö
¿µ¹® ³í¹®Áö
±¹³» ÇÐȸÁö
Çмú´ëȸ ÇÁ·Î½Ãµù
±¹³» ÇÐÀ§ ³í¹®
³í¹®Á¤º¸
¹é¼
±³À°Á¤º¸
¿¬±¸ ù°ÉÀ½
ÇаúÁ¤º¸
°ÀÇÁ¤º¸
µ¿¿µ»óÁ¤º¸
E-Learning
¿Â¶óÀÎ Àú³Î
½ÉÈÁ¤º¸
¿¬±¸ ¹× ±â¼úµ¿Çâ
Áֿ俬±¸ÅäÇÈ
ÁÖ¿ä°úÁ¦ ¹× ±â°ü
Çؿܱâ°ü °ü·ÃÀÚ·á
¹ÙÀÌ¿À Á¤º¸±â¼ú
ÁÖ¿ä Archive Site
Æ÷Ä¿½ºiN
¿¬±¸ÀÚ Á¤º¸
¶óÀÌ¡½ºÅ¸
ÆÄ¿öiNÅͺä
¼¼ÁßÇÑ
¿¬±¸ÀÚ·á
¹®ÀÚ DB
¿ë¾î»çÀü
¾Ë¸²¸¶´ç
ºÎ½Ç ÇмúÈ°µ¿ ¿¹¹æ
³í¹®¸ðÁý
´ëȸ¾È³»
What's New
¿¬±¸ºñÁ¤º¸
±¸ÀÎÁ¤º¸
°øÁö»çÇ×
CSERIC ±¤Àå
Post-Conference
¿¬±¸ÀÚ Ä«Æä
ÀÚÀ¯°Ô½ÃÆÇ
Q&A
´Ý±â
»çÀÌÆ®¸Ê
¿¬±¸¹®Çå
±¹³» ³í¹®Áö
¿µ¹® ³í¹®Áö
±¹³» ÇÐȸÁö
Çмú´ëȸ ÇÁ·Î½Ãµù
±¹³» ÇÐÀ§ ³í¹®
³í¹®Á¤º¸
¹é¼
±³À°Á¤º¸
¿¬±¸ ù°ÉÀ½
ÇаúÁ¤º¸
°ÀÇÁ¤º¸
µ¿¿µ»óÁ¤º¸
E-Learning
¿Â¶óÀÎ Àú³Î
½ÉÈÁ¤º¸
¿¬±¸ ¹× ±â¼úµ¿Çâ
Áֿ俬±¸ÅäÇÈ
ÁÖ¿ä°úÁ¦ ¹× ±â°ü
Çؿܱâ°ü °ü·ÃÀÚ·á
¹ÙÀÌ¿À Á¤º¸±â¼ú
ÁÖ¿ä Archive Site
ÄÄÇ»ÅÍiN
¿¬±¸ÀÚ Á¤º¸
¿¬±¸ÀÚ·á
¹®ÀÚ DB
Ȧ·Î±×·¥ DB
¿ë¾î»çÀü
¾Ë¸²¸¶´ç
ºÎ½Ç ÇмúÈ°µ¿ ¿¹¹æ
³í¹®¸ðÁý
´ëȸ¾È³»
What's New
¿¬±¸ºñ Á¤º¸
±¸ÀÎÁ¤º¸
°øÁö»çÇ×
IT Daily
CSERIC ±¤Àå
Post-Conference
¿¬±¸ÀÚ Ä«Æä
ÀÚÀ¯°Ô½ÃÆÇ
Q&A
¼ºñ½º ¹Ù·Î°¡±â
¼³¹®Á¶»ç
¿¬±¸À±¸®
°ü·Ã±â°ü
Please wait....
¿¬±¸¹®Çå
±¹³» ³í¹®Áö
¿µ¹® ³í¹®Áö
±¹³» ÇÐȸÁö
Çмú´ëȸ ÇÁ·Î½Ãµù
±¹³» ÇÐÀ§ ³í¹®
³í¹®Á¤º¸
¹é¼
¿µ¹® ³í¹®Áö
Ȩ > ¿¬±¸¹®Çå > ¿µ¹® ³í¹®Áö >
TIIS (Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ)
TIIS (Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ)
Current Result Document :
1
/ 3
´ÙÀ½°Ç
ÇѱÛÁ¦¸ñ(Korean Title)
Defending and Detecting Audio Adversarial Example using Frame Offsets
¿µ¹®Á¦¸ñ(English Title)
Defending and Detecting Audio Adversarial Example using Frame Offsets
ÀúÀÚ(Author)
Yongkang Gong
Diqun Yan
Terui Mao
Donghua Wang
Rangding Wang
¿ø¹®¼ö·Ïó(Citation)
VOL 15 NO. 4 PP. 1538 ~ 1552 (2021. 04)
Çѱ۳»¿ë
(Korean Abstract)
¿µ¹®³»¿ë
(English Abstract)
Machine learning models are vulnerable to adversarial examples generated by adding a deliberately designed perturbation to a benign sample. Particularly, for automatic speech recognition (ASR) system, a benign audio which sounds normal could be decoded as a harmful command due to potential adversarial attacks. In this paper, we focus on the countermeasures against audio adversarial examples. By analyzing the characteristics of ASR systems, we find that frame offsets with silence clip appended at the beginning of an audio can degenerate adversarial perturbations to normal noise. For various scenarios, we exploit frame offsets by different strategies such as defending, detecting and hybrid strategy. Compared with the previous methods, our proposed method can defense audio adversarial example in a simpler, more generic and efficient way. Evaluated on three state-of-the-arts adversarial attacks against different ASR systems respectively, the experimental results demonstrate that the proposed method can effectively improve the robustness of ASR systems.
Å°¿öµå(Keyword)
Speech Recognition Safety
Adversarial Defense
Adversarial Detection
Audio Adversarial Example
ASR
ÆÄÀÏ÷ºÎ
PDF ´Ù¿î·Îµå
¸ñ·Ï
Copyright(c)
Computer Science Engineering Research Information Center
. All rights reserved.