AI RESEARCH
Robustness Verification of Polynomial Neural Networks
arXiv CS.LG
•
ArXi:2602.06105v2 Announce Type: replace-cross We study robustness verification of neural networks via metric algebraic geometry. For polynomial neural networks, certifying a robustness radius amounts to computing the distance to the algebraic decision boundary. We use the Euclidean distance (ED) degree as an intrinsic measure of the complexity of this problem, analyze the associated ED discriminant, and