In order to generate high-quality electromagnetic signal countermeasure examples,a fast Jacobian saliency map attack(FJSMA)method was proposed.The Jacobian matrix of the attack target class was calculated and feature sa-liency maps based on the matrix were generated,then the most salient feature points were iteratively selected and pertur-bations in their neighborhood were continuously added while introducing a single point perturbation constraint,finally adversarial examples were generated.Experimental results show that,compared with Jacobian saliency map attack method,FJSMA improves the generation speed by about 10 times while maintaining the same high attack success rate,and improves the similarity by more than 11%,and compared with other gradient-based methods,the attack success rate is improved by more than 20%,and the similarity is improved by 20%to 30%.
关键词
深度神经网络/对抗样本/电磁信号调制识别/雅可比显著图/目标攻击
Key words
deep neural network/adversarial sample/electromagnetic signal modulation recognition/Jacobian saliency map/target attack
维普
万方数据