Training for faster adversarial robustness verification via inducing Relu stability
Name
1809.03008.pdf
Description
Accepted version
Size
753.62 KB
Format
Adobe PDF
Checksum (MD5)
5fb30e47befb84881909e316824f0ecd
Author(s)
Xiao, Kai Yuanqing
Tjeng, Vincent
Shafiullah, Nur Muhammad Mahi.
Mądry, Aleksander
Date Issued
May 2019
Journal
7th International Conference on Learning Representations, ICLR 2019
Publisher
ICLR
Citation
Xiao, Kai Y. et al. “Training for faster adversarial robustness verification via inducing Relu stability.” Paper presented at the 7th International Conference on Learning Representations, ICLR 2019, New Orleans, Louisiana, May 6 - 9, 2019, ICLR © 2019 The Author(s)
Version
Author's final manuscript
Abstract
We explore the concept of co-design in the context of neural network verification. Specifically, we aim to train deep neural networks that not only are robust to adversarial perturbations but also whose robustness can be verified more easily. To this end, we identify two properties of network models - weight sparsity and so-called ReLU stability - that turn out to significantly impact the complexity of the corresponding verification task. We demonstrate that improving weight sparsity alone already enables us to turn computationally intractable verification problems into tractable ones. Then, improving ReLU stability leads to an additional 4-13x speedup in verification times. An important feature of our methodology is its “universality,” in the sense that it can be used with a broad range of training procedures and verification approaches.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
