1. Provable defenses against adversarial examples via the convex outer adversarial polytope;wong;Int Conference on Machine Learning,2018
2. A convex relaxation barrier to tight ro-bust verification of neural networks;salman;ArXiv Preprint,2019
3. Efficient formal safety analysis of neural networks;wang;ArXiv Preprint,2018
4. Fast and effective robustness certification;singh;NeurIPS,2018
5. Towards fast computation of certified robustness for relu networks;weng;Int Conference on Machine Learning,2018