Fastened CROWN: Tightened Neural Network Robustness Certificates
Name
5944-Article Text-9169-1-10-20200513.pdf
Description
Published version
Size
937.2 KB
Format
Adobe PDF
Checksum (MD5)
0726e75bebcfc674c48b21742a3c2d02
Author(s)
Lyu, Zhaoyang
Ko, Ching-Yun
Kong, Zhifeng
Wong, Ngai
Lin, Dahua
Daniel, Luca
Date Issued
2020
Journal
Proceedings of the AAAI Conference on Artificial Intelligence
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Citation
Lyu, Zhaoyang, Ko, Ching-Yun, Kong, Zhifeng, Wong, Ngai, Lin, Dahua et al. 2020. "Fastened CROWN: Tightened Neural Network Robustness Certificates." Proceedings of the AAAI Conference on Artificial Intelligence, 34 (04).
Version
Final published version
Abstract
The rapid growth of deep learning applications in real life is accompanied by severe safety concerns. To mitigate this uneasy phenomenon, much research has been done providing reliable evaluations of the fragility level in different deep neural networks. Apart from devising adversarial attacks, quantifiers that certify safeguarded regions have also been designed in the past five years. The summarizing work in (Salman et al. 2019) unifies a family of existing verifiers under a convex relaxation framework. We draw inspiration from such work and further demonstrate the optimality of deterministic CROWN (Zhang et al. 2018) solutions in a given linear programming problem under mild constraints. Given this theoretical result, the computationally expensive linear programming based method is shown to be unnecessary. We then propose an optimization-based approach FROWN (Fastened CROWN): a general algorithm to tighten robustness certificates for neural networks. Extensive experiments on various networks trained individually verify the effectiveness of FROWN in safeguarding larger robust regions.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1609/AAAI.V34I04.5944
