Improved Training of Certifiably Robust Models

25 Sep 2019  ·  Chen Zhu, Renkun Ni, Ping-Yeh Chiang, Hengduo Li, Furong Huang, Tom Goldstein ·

Convex relaxations are effective for training and certifying neural networks against norm-bounded adversarial attacks, but they leave a large gap between certifiable and empirical (PGD) robustness. In principle, relaxation can provide tight bounds if the convex relaxation solution is feasible for the original non-relaxed problem. Therefore, we propose two regularizers that can be used to train neural networks that yield convex relaxations with tighter bounds. In all of our experiments, the proposed regularizations result in tighter certification bounds than non-regularized baselines.

PDF Abstract
No code implementations yet. Submit your code now



  Add Datasets introduced or used in this paper

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here