Research Article

Robustness and Explainability of Image Classification Based on QCNN

Table 3

QCNN accuracy against different adversarial attacks.

TypesFGSMCWJSMADeepFool

Attacks0.89060.89060.84380.8750
Bitplane10.74980.74650.75990.7364
Bitplane20.72360.72830.76810.7826
Bitplane30.79420.75630.80130.7169
Bitplane40.80450.79540.78420.7765
Bitplane50.92190.81120.87500.8906
Bitplane60.89060.92190.71880.9375
Bitplane70.93750.90620.87280.9062
Bitplane80.95310.76560.85940.9219