Skip to main content

Table 1 Results of conducting the proposed attack on all convolutional network (AllConv) with different F values

From: Attacking convolutional neural network using differential evolution

Variant

Success rate (%)

Confidence (%)

Cost

0.5/0.5/0.5

71.46

89.38

24.66

0.9/0.5/0.5

72.00

88.22

25.71

0.1/0.5/0.5

70.63

90.86

20.32

  1. Among the measures in the first row, the cost indicates the average distortion in pixel values per channel per pixel