Randomized Adversarial Training via Taylor Expansion

Understand

In recent years, there has been an explosion of research into developing more robust deep neural networks against adversarial examples.

• Adversarial training appears as one of the most successful methods.
• To deal with both the robustness against adversarial examples and the accuracy over clean examples, many works develop enhanced adversarial training methods to achieve various trade-offs between them.
• Leveraging over the studies that smoothed update on weights during training may help find flat minima and improve generalization, we suggest reconciling the robustness-accuracy trade-off from another perspective, i.e., by adding random noise into deterministic weights.