【作者】Yun Lin,Haojun Zhao,Xuefei Ma,Ya Tu,Meiyu Wang
【作者单位】1 College of Information and Communication Engineering, Harbin Engineering University, Harbin, China 2 Acoustic Science and Technology Laboratory, Harbin Engineering University, Harbin, China 3 College of Underwater Acoustic Engineering, Harbin Engineering University, Harbin, China 4 School of Information Science and Technology, Tibet University, Tibet, China
【摘要】 Deep learning models are vulnerable to adversarial attacks, by adding a subtle perturbation which is imperceptible to the human eye, a convolutional neural network can lead to erroneous results, which greatly reduces the reliability and security of...