ZeroGrad : Mitigating and Explaining Catastrophic Overfitting in FGSM Adversarial Training

Understand

Making deep neural networks robust to small adversarial noises has recently been sought in many applications.

• Adversarial training through iterative projected gradient descent (PGD) has been established as one of the mainstream ideas to achieve this goal.
• However, PGD is computationally demanding and often prohibitive in case of large datasets and models.
• For this reason, single-step PGD, also known as FGSM, has recently gained interest in the field.