通过深度自适应的随机丢弃提升神经网络抗攻击能力
Adversarial robustness through Lipschitz-Guided Stochastic Depth in Neural Networks
- 按深度递增设置丢弃概率，控制网络整体光滑性
- 在CIFAR-10上实现更强的对抗鲁棒性且计算量更低
- 适合追求高效可靠防御的视觉模型研究者
深度神经网络和视觉变换器在计算机视觉中表现优异，但对对抗扰动极为敏感。传统防御方法常伴随高计算开销或缺乏理论保障。本文提出一种基于Lipschitz约束的深度自适应随机深度（DropPath）方法，使丢弃概率随网络深度增加，以控制网络的有效Lipschitz常数。该方法对深层网络进行正则化，在保持干净准确率的同时提升鲁棒性并降低计算量。在CIFAR-10数据集上使用ViT-Tiny进行实验，结果表明：所提出的深度依赖调度方案维持了接近基线的干净准确率，显著增强了对FGSM、PGD-20和AutoAttack的鲁棒性，且相比基线与线性丢弃调度大幅减少浮点运算量（FLOPs）。
原文摘要 · Abstract (English)
Deep neural networks and Vision Transformers achieve state-of-the-art performance in computer vision but are highly vulnerable to adversarial perturbations. Standard defenses often incur high computational cost or lack formal guarantees. We propose a Lipschitz-guided stochastic depth (DropPath) method, where drop probabilities increase with depth to control the effective Lipschitz constant of the network. This approach regularizes deeper layers, improving robustness while preserving clean accuracy and reducing computation. Experiments on CIFAR-10 with ViT-Tiny show that our custom depth-dependent schedule maintains near-baseline clean accuracy, enhances robustness under FGSM, PGD-20, and AutoAttack, and significantly reduces FLOPs compared to baseline and linear DropPath schedules.
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。