6 citations · 8 across the 2 of their papers we have counts for
2 papers
cs.LG2023★ 6 cited
A Tale of Two Approximations: Tightening Over-Approximation for DNN Robustness Verification via Under-Approximation
Zhiyi Xue, Si Liu, Zhaodi Zhang +2
The robustness of deep neural networks (DNNs) is crucial to the hosting system's reliability and security. Formal verification has been demonstrated to be effective in providing pr…
cs.CV2023★ 2 cited
Boosting Verified Training for Robust Image Classifications via Abstraction
Zhaodi Zhang, Zhiyi Xue, Yang Chen +4
This paper proposes a novel, abstraction-based, certified training method for robust image classifiers. Via abstraction, all perturbed images are mapped into intervals before feedi…