通过训练集中的脆弱样本评估模型鲁棒性，提升可靠性。
A Validation Strategy for Deep Learning Models: Evaluating and Enhancing Robustness
- 从训练集提取最易受干扰的脆弱样本
- 在脆弱样本上评估能提前发现模型缺陷
- 适合关注模型安全性的研究者和工程师
数据驱动模型，尤其是深度学习分类器，在干净数据集上表现优异，但对常见数据畸变（如对抗攻击和常规噪声）仍显脆弱。这些扰动会显著降低性能，威胁模型整体可靠性。传统鲁棒性验证依赖带扰动的测试集，而本文提出新方法：通过局部鲁棒性分析，直接从训练集中提取“弱鲁棒”样本。这些最易受扰动的样本成为模型脆弱性的早期敏感指标。在这些挑战性训练样本上评估模型，可获得更细致的鲁棒性认知，并指导针对性优化。我们在CIFAR-10、CIFAR-100和ImageNet上验证了该方法的有效性，表明基于弱鲁棒样本的验证能显著提升模型在对抗攻击与常见畸变场景下的可靠性。
原文摘要 · Abstract (English)
Data-driven models, especially deep learning classifiers often demonstrate great success on clean datasets. Yet, they remain vulnerable to common data distortions such as adversarial and common corruption perturbations. These perturbations can significantly degrade performance, thereby challenging the overall reliability of the models. Traditional robustness validation typically relies on perturbed test datasets to assess and improve model performance. In our framework, however, we propose a validation approach that extracts "weak robust" samples directly from the training dataset via local robustness analysis. These samples, being the most susceptible to perturbations, serve as an early and sensitive indicator of the model's vulnerabilities. By evaluating models on these challenging training instances, we gain a more nuanced understanding of its robustness, which informs targeted performance enhancement. We demonstrate the effectiveness of our approach on models trained with CIFAR-10, CIFAR-100, and ImageNet, highlighting how robustness validation guided by weak robust samples can drive meaningful improvements in model reliability under adversarial and common corruption scenarios.
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。