# A Tool for Neural Network Global Robustness Certification and Training

arXiv: https://arxiv.org/abs/2208.07289 · HTML: https://mlsanity.com/paper/2208.07289/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 6 references that are in the map.
- First posted on arXiv 15 Aug 2022.

## Builds on (most cited first, 3 of 3)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verification](https://mlsanity.com/paper/2103.06624/) (2021)
- [Efficient Global Robustness Certification of Neural Networks via Interleaving Twin-Network Encoding](https://mlsanity.com/paper/2203.14141/) (2022)

## Built on by (most cited first, 5 of 5)

- [Verification of Neural Networks' Global Robustness](https://mlsanity.com/paper/2402.19322/) (2024)
- [Robustness Verification of Deep Neural Networks using Star-Based Reachability Analysis with Variable-Length Time Series Input](https://mlsanity.com/paper/2307.13907/) (2023)
- [gRoMA: a Tool for Measuring the Global Robustness of Deep Neural Networks](https://mlsanity.com/paper/2301.02288/) (2023)
- [The Pros and Cons of Adversarial Robustness](https://mlsanity.com/paper/2312.10911/) (2023)
- [Formal Verification of Long Short-Term Memory based Audio Classifiers: A Star based Approach](https://mlsanity.com/paper/2311.12130/) (2023)

## Abstract (arXiv)

With the increment of interest in leveraging machine learning technology in safety-critical systems, the robustness of neural networks under external disturbance receives more and more concerns. Global robustness is a robustness property defined on the entire input domain. And a certified globally robust network can ensure its robustness on any possible network input. However, the state-of-the-art global robustness certification algorithm can only certify networks with at most several thousand neurons. In this paper, we propose the GPU-supported global robustness certification framework GROCET, which is more efficient than the previous optimization-based certification approach. Moreover, GROCET provides differentiable global robustness, which is leveraged in the training of globally robust neural networks.