Physical Sciences and Mathematics Commons^™

Deepcause: Verifying Neural Networks With Abstraction Refinement, Nguyen Hua Gia Phuc

Dissertations and Theses Collection (Open Access)

Neural networks have been becoming essential parts in many safety-critical systems (such
as self-driving cars and medical diagnosis). Due to that, it is desirable that neural networks
not only have high accuracy (which traditionally can be validated using a test set) but also
satisfy some safety properties (such as robustness, fairness, or free of backdoor). To verify
neural networks against desired safety properties, there are many approaches developed
based on classical abstract interpretation. However, like in program verification, these
approaches suffer from false alarms, which may hinder the deployment of the networks.

One natural remedy to tackle the problem adopted …