Skip to main content

Table 4 Compassion of attack effectiveness between the proposed method with DE 0.1/0.1/0.1 and three previous works: LSA [15], FGSM [8], and one-pixel [23], which shows that even under more restricted condition, the proposed method can still perform comparative effectiveness to previous works

From: Attacking convolutional neural network using differential evolution

Method

Success rate (%)

Confidence (%)

Number (percentage) of pixels

Network

0.1/0.1/0.1

72.30

83.63

5 (0.48%)

NiN

0.1/0.1/0.1

56.49

67.36

5 (0.48%)

VGG

0.1/0.1/0.1

71.86

90.30

5 (0.48%)

AllConv

LSA

97.89

72

33 (3.24%)

NiN

LSA

97.98

77

30 (2.99%)

VGG

FGSM

93.67

93

1024 (100%)

NiN

FGSM

90.93

90

1024 (100%)

VGG

One-pixel

72.85

75.02

1 (0.098%)

NiN

One-pixel

63.53

65.25

1 (0.098%)

VGG

One-pixel

68.71

79.4

1 (0.098%)

AllConv