Wang, Zhilu, Huang, Chao 
ORCID: 0000-0002-9300-1787 and Zhu, Qi
(2022)
Efficient Global Robustness Certification of Neural Networks via
Interleaving Twin-Network Encoding.
In: Design, Automation and Test in Europe Conference, 2022-3-14 - 2022-3-23, ANTWERP, BELGIUM.
|
Text
Global_Robustness__DATE_22___camera_ready_.pdf - Author Accepted Manuscript Download (497kB) | Preview |
Abstract
The robustness of deep neural networks has received significant interest recently, especially when being deployed in safety-critical systems, as it is important to analyze how sensitive the model output is under input perturbations. While most previous works focused on the local robustness property around an input sample, the studies of the global robustness property, which bounds the maximum output change under perturbations over the entire input space, are still lacking. In this work, we formulate the global robustness certification for neural networks with ReLU activation functions as a mixed-integer linear programming (MILP) problem, and present an efficient approach to address it. Our approach includes a novel interleaving twin-network encoding scheme, where two copies of the neural network are encoded side-by-side with extra interleaving dependencies added between them, and an over-approximation algorithm leveraging relaxation and refinement techniques to reduce complexity. Experiments demonstrate the timing efficiency of our work when compared with previous global robustness certification methods and the tightness of our over-approximation. A case study of closed-loop control safety verification is conducted, and demonstrates the importance and practicality of our approach for certifying the global robustness of neural networks in safety-critical systems.
| Item Type: | Conference or Workshop Item (Unspecified) |
|---|---|
| Additional Information: | Published at DATE 2022 |
| Uncontrolled Keywords: | cs.LG, cs.LG, cs.RO, cs.SY, eess.SY |
| Divisions: | Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science |
| Depositing User: | Symplectic Admin |
| Date Deposited: | 26 Nov 2021 08:26 |
| Last Modified: | 18 Jan 2023 21:24 |
| Related URLs: | |
| URI: | https://livrepository.liverpool.ac.uk/id/eprint/3143864 |
Share
Share
