Research of Adversarial Samples Attacksand Defenses Methods in Deep Learning
This paper introduces the concept of adversarial samples and explores the reasons for the generation of adversarial samples firstly.Secondly,it analyzes the classical adversarial samples attack methods from different fields and expounds the main adversarial samples defense methods from different research directions.Finally,it reviews the advantages and disadvantages of the existing research results and gives the future development trend of adversarial sample research.
deep learningdeep neural networkadversarial samplesadversarial attacks and defen-sesartificial intelligence
万方数据
维普
