MemLoss: Enhancing Adversarial Training with Recycling Adversarial Examples
This is an incremental improvement for enhancing model robustness in adversarial machine learning.
The paper tackled improving adversarial training by recycling adversarial examples across epochs, resulting in better accuracy on datasets like CIFAR-10 while maintaining strong robustness against attacks.
In this paper, we propose a new approach called MemLoss to improve the adversarial training of machine learning models. MemLoss leverages previously generated adversarial examples, referred to as 'Memory Adversarial Examples,' to enhance model robustness and accuracy without compromising performance on clean data. By using these examples across training epochs, MemLoss provides a balanced improvement in both natural accuracy and adversarial robustness. Experimental results on multiple datasets, including CIFAR-10, demonstrate that our method achieves better accuracy compared to existing adversarial training methods while maintaining strong robustness against attacks.