Algorithm 1: Image Adversarial Example Generation Method Based on Adaptive Parameter Adjustable Differential Evolution

(1) Input: Original image $\mathrm{I}$ and its correct label $\mathrm{t}$ (2) Output: Adversarial example I’, or original image $\mathrm{I}$. (3) $\mathrm{x}=\left({\mathrm{x}}_1,{\mathrm{x}}_2,\dots ,{\mathrm{x}}_{\mathrm{n}}\right)\leftarrow \mathrm{I}$ (4) $\mathrm{p}\left(\mathrm{x}\right)=\left({\mathrm{p}}_1,{\mathrm{p}}_2,\dots ,{\mathrm{p}}_{\mathrm{n}}\right)$ (5) flag, image $\leftarrow$ APADE(x, t, $\mathrm{p}\left(\mathrm{x}\right)$) (6) if flag == Success (7)   return I′ (8) else (9)   return I (10)end if