Adaptive perturbation adversarial training: based on reinforcement learning

Understand

Adversarial training has become the primary method to defend against adversarial samples.

• However, it is hard to practically apply due to many shortcomings.
• One of the shortcomings of adversarial training is that it will reduce the recognition accuracy of normal samples.
• Adaptive perturbation adversarial training is proposed to alleviate this problem.