Figure 6.

Diagram depicts the detailed generalization analysis experiment of DNN and SAN, showing the generalization test results of the DNN under different training steps, which represent different scales of overfitting. As the number of training steps increases, the generalization performance of DNN gradually improves. The generalization test results for DNN exhibit a similar pattern of DNN-type, while the results for SAN also exhibit a similar pattern of SAN-type. By comparing these two patterns, we can see that SAN has better generalization ability and robustness.