Cross-representation transferable adversarial examples generation for audio classification

Adversarial examples have been used as an important tool for detecting vulnerabilities in deep neural networks. The unique property of transferability enables them to deceive black-box deep neural network models. Transfer-based attack methods for audio classification have recently attracted extensiv...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριοι συγγραφείς:	TIAN Zilin, LONG Yunfei, TIAN Ye, ZHANG Liguo
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	POSTS&TELECOM PRESS Co., LTD 2025-04-01
Σειρά:	网络与信息安全学报
Θέματα:	adversarial example transfer-based attack audio classification attack cross-representation
Διαθέσιμο Online:	http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2025022
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!