Tag
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 introduces a neural architecture with learnable polynomial layers and differential regularization, achieving sample-efficient, robust performance across tabular, NLP, and vision tasks with results on Pima Diabetes, SST-5, Yelp Full, and CIFAR-10-C.