复用对抗样本提升模型鲁棒性，不损失干净数据表现
MemLoss: Enhancing Adversarial Training with Recycling Adversarial Examples
- 将历史对抗样本存入内存，在后续训练中重复使用
- 在CIFAR-10上比现有方法更高自然准确率，同时保持强抗攻击能力
- 适合需要兼顾精度与安全性的实际部署场景
本文提出一种名为MemLoss的新方法，用于改进机器学习模型的对抗训练。MemLoss利用之前生成的对抗样本（称为'记忆对抗样本'），在不牺牲干净数据性能的前提下，提升模型的鲁棒性和准确率。通过跨训练轮次复用这些样本，MemLoss实现了自然准确率与对抗鲁棒性的均衡提升。在CIFAR-10等多个数据集上的实验结果表明，该方法在准确率上优于现有对抗训练方法，同时对各类攻击仍保持强鲁棒性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。