Engineering Commons^™

Formal Verification Of The Adversarial Robustness Property Of Deep Neural Networks Through Dimension Reduction Heuristics, Refutation-Based Abstraction, And Partitioning, Joshua Smith

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Neural networks are tools that are often used to perform functions such as object recognition in images, speech-to-text, and general data classification. Because neural networks have been successful at approximating these functions that are difficult to explicitly write, they are seeing increased usage in fields such as autonomous driving, airplane collision avoidance systems, and other safety-critical applications. Due to the risks involved with safety-critical systems, it is important to provide guarantees about the networks performance under certain conditions. As an example, it is critically important that self driving cars with neural network based vision systems correctly identify pedestrians 100% of …