Skip to main content

Table 3 Results of conducting proposed attacks on additional datasets by using local-optimized DE 0.1/0.1/0.1 and 0.5/0.1/0.1

From: Attacking convolutional neural network using differential evolution

Variant

Success rate (%)

Confidence (%)

Cost

All convolutional net

   

0.1/0.1/0.1

71.86

90.30

20.44

0.5/0.1/0.1

72.29

88.68

24.64

Network in network

   

0.1/0.1/0.1

72.30

83.63

14.28

0.5/0.1/0.1

70.63

81.17

16.30

VGG network

   

0.1/0.1/0.1

56.49

67.36

22.98

0.5/0.1/0.1

61.28

73.07

24.62

BVLC network

   

0.1/0.1/0.1

31.87

14.88

2.36

0.5/0.1/0.1

26.69

14.79

6.19