A linear constraint driven approach to efficiently enhancing branch and bound in neural network verification

Chavez, Jorge

Permalink

https://hdl.handle.net/2142/129353 Copy

Description

Title

A linear constraint driven approach to efficiently enhancing branch and bound in neural network verification

Author(s)

Chavez, Jorge

Issue Date

2025-05-09

Director of Research (if dissertation) or Advisor (if thesis)

Zhang, Huan

Department of Study

Electrical & Computer Eng

Discipline

Electrical & Computer Engr

Degree Granting Institution

University of Illinois Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

Machine Learning, Neural Network Verification

Abstract

The verification of neural network systems is crucial as the adoption of these systems are considered for safety-critical tasks. A neural network system that works empirically well may not be robust, and when employed in areas such as cyber-security and cyber-physical systems, the guaranteed performance is a must. Formal verification is a rapidly growing field that delves into providing these guarantees, ensuring that properties on these networks can be assured. This thesis serves as an introduction into the common techniques used to provide such guarantees. There is a particular focus on bound propagation techniques as such techniques have fueled state-of-the-art, efficient verifiers. After covering the many advances that have been made in neural network verification, we will delve further into the branch-and-bound paradigm that typically accompanies many existing verifiers, as well as demonstrate an insightful algorithm that is capable of garnering further efficacy from bound propagation verifiers.

Graduation Semester

2025-05

Type of Resource

Thesis

Handle URL

https://hdl.handle.net/2142/129353

Copyright and License Information

Copyright 2025 Jorge Chavez

Owning Collections