Search Results for author:
Found 5 papers, 1 papers with code
A Tale of Two Approximations: Tightening Over-Approximation for DNN Robustness Verification via Under-Approximation
In this paper, we study existing approaches and identify a dominant factor in defining tight approximation, namely the approximation domain of the activation function.
Boosting Verified Training for Robust Image Classifications via Abstraction
Via abstraction, all perturbed images are mapped into intervals before feeding into neural networks for training.
DualApp: Tight Over-Approximation for Neural Network Robustness Verification via Under-Approximation
We observe that existing approaches only rely on overestimated domains, while the corresponding tight approximation may not necessarily be tight on its actual domain.
Provably Tightest Linear Approximation for Robustness Verification of Sigmoid-like Neural Networks
Considerable efforts have been devoted to finding the so-called tighter approximations to obtain more precise verification results.
Accelerating Robustness Verification of Deep Neural Networks Guided by Target Labels
The key insight of our approach is that the robustness verification problem of DNNs can be solved by verifying sub-problems of DNNs, one per target label.
