Improving the Imperceptibility of Adversarial Examples Based on Weakly Perceptual Perturbation in Key Regions

<table class="table-group" id="tab3"><tr><td><table class="table"><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr class="thead"><td class="align_left">Method</td><td class="align_center">mAP<sub>ori</sub></td><td class="align_center">mAP<sub>adv</sub></td><td class="align_center">ASR</td></tr><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr><td class="align_left">DAG</td><td class="align_center">0.70</td><td class="align_center">0.05</td><td class="align_center">0.93</td></tr><tr><td class="align_left">UEA</td><td class="align_center">0.70</td><td class="align_center">0.05</td><td class="align_center">0.93</td></tr><tr><td class="align_left">WPAE</td><td class="align_center">0.70</td><td class="align_center">0.02</td><td class="align_center">0.97</td></tr><tr class="table-tr"><td colspan="4"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Comparison of the white box attack success rate.</div>

Security and Communication Networks

tab3

Table 3

Table 3: Improving the Imperceptibility of Adversarial Examples Based on Weakly Perceptual Perturbation in Key Regions 