Efficient text-based evolution algorithm to hard-label adversarial attacks on text

Deep neural networks that play a pivotal role in fields such as images, text, and audio are vulnerable to adversarial attacks. In current textual adversarial attacks, the vast majority are configured with a black-box soft-label which is achieved by the gradient information or confidence of the model...

תיאור מלא

מידע ביבליוגרפי

Principais autores:	Hao Peng, Zhe Wang, Dandan Zhao, Yiming Wu, Jianming Han, Shixin Guo, Shouling Ji, Ming Zhong
פורמט:	Artigo
שפה:	Inglês
יצא לאור:	Springer 2023-05-01
סדרה:	Journal of King Saud University: Computer and Information Sciences
נושאים:	Natural language processing Machine learning Language model Adversarial attack Black-box attack Hard-label
גישה מקוונת:	http://www.sciencedirect.com/science/article/pii/S131915782300085X
תגים:	הוספת תג אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!