用极值理论让分类器自动拒绝异常样本，效果可证明。
Provably Safeguarding a Classifier from OOD and Adversarial Samples: an Extreme Value Theory Approach
- 用极值理论建模训练数据分布，识别异常输入
- 在多个数据集上拒识率超95%，且不依赖额外训练
- 适合对安全性要求高的场景，如自动驾驶
本文提出一种名为SPADE的新方法，通过在分类器的隐空间中构建广义极值（GEV）模型，实现对分布外（OOD）和对抗样本的可证明防护。该方法将原始分类器转化为拒绝式分类器，基于GEV模型评估样本并决定是否拒绝。在温和假设下，该模型不仅能形式化刻画分布外样本，还能形式化刻画对抗样本。实验在ResNet、VGG与Vision Transformer等多类神经网络架构，以及CIFAR-10、CIFAR-100和ImageNet等中大型数据集上验证了其有效性，结果表明该方法在保持高精度的同时具备低资源消耗、稳定性和高效性，优于当前主流方法。
原文摘要 · Abstract (English)
This paper introduces a novel method, Sample-efficient Probabilistic Detection using Extreme Value Theory (SPADE), which transforms a classifier into an abstaining classifier, offering provable protection against out-of-distribution and adversarial samples. The approach is based on a Generalized Extreme Value (GEV) model of the training distribution in the classifier's latent space, enabling the formal characterization of OOD samples. Interestingly, under mild assumptions, the GEV model also allows for formally characterizing adversarial samples. The abstaining classifier, which rejects samples based on their assessment by the GEV model, provably avoids OOD and adversarial samples. The empirical validation of the approach, conducted on various neural architectures (ResNet, VGG, and Vision Transformer) and medium and large-sized datasets (CIFAR-10, CIFAR-100, and ImageNet), demonstrates its frugality, stability, and efficiency compared to the state of the art.
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。