gradient-regularization

This paper introduces a white-box, gradient-regularized evasion framework that embeds attack logic directly into model parameters, successfully fooling explainable AI auditors like LIME, SHAP, and Integrated Gradients while bypassing anomaly detection defenses.

ChainzRule 提出了一种具有可学习多项式层和微分正则化的神经架构，在表格、NLP和视觉任务上实现了样本高效且鲁棒的性能，在Pima Diabetes、SST-5、Yelp Full和CIFAR-10-C数据集上取得了成果。