用约束优化提升神经网络抗对抗攻击能力，精度损失极小
A constrained optimization approach to improve robustness of neural networks
- 引入对抗修正约束，确保对抗样本分类正确
- 仅用少量对抗数据就显著提升鲁棒性，准确率基本不变
- 基于切平面的算法高效求解大规模非凸问题，适合实际应用
本文提出一种基于非线性规划的新方法，用于微调预训练神经网络，在保持干净数据高准确率的同时提升对对抗攻击的鲁棒性。该方法引入对抗修正约束，确保对抗样本被正确分类，并最小化模型参数的改动。我们设计了一种高效的基于切平面的算法，通过多面体切片逼近可行域，平衡鲁棒性与准确率之间的权衡。在MNIST和CIFAR10等标准数据集上的实验表明，即使使用极少数量的对抗样本，该方法也能显著提升模型鲁棒性，同时对准确率影响极小。
原文摘要 · Abstract (English)
In this paper, we present a novel nonlinear programming-based approach to fine-tune pre-trained neural networks to improve robustness against adversarial attacks while maintaining high accuracy on clean data. Our method introduces adversary-correction constraints to ensure correct classification of adversarial data and minimizes changes to the model parameters. We propose an efficient cutting-plane-based algorithm to iteratively solve the large-scale nonconvex optimization problem by approximating the feasible region through polyhedral cuts and balancing between robustness and accuracy. Computational experiments on standard datasets such as MNIST and CIFAR10 demonstrate that the proposed approach significantly improves robustness, even with a very small set of adversarial data, while maintaining minimal impact on accuracy.
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。