Provably reliable machine learning systems

Machine learning systems, which primarily use deep neural networks (DNNs), serve as critical components in safety-critical applications and compound AI systems. Despite their ubiquity, automated formal reasoning about their reliability has lagged significantly. Neural network verification is NP-hard, requiring expensive end-to-end recomputation whenever networks are modified during iterative deployment cycles. Simultaneously, Large Language Models (LLMs) in compound systems frequently generate outputs that violate syntactic and semantic specifications, leading to cascading failures in automated workflows. Thus, developing reliability techniques for machine learning systems that are simultaneously general, precise, and scalable remains a challenging task. To address these challenges, this dissertation develops a comprehensive framework for provably reliable machine learning systems by establishing incremental verification techniques for DNNs and constrained decoding methods specific to LLMs.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois Urbana-Champaign

Year dc:date

2025

Author dc:creator

• Ugare, Shubham

Contributors dc:contributor

• Singh, Gagandeep
• Misailovic, Sasa
• Zhang, Lingming
• Chaudhuri, Swarat

• Machine Learning, Formal Methods

Statement dc:rights

• Copyright 2025 Shubham Ugare

Language dc:language

en

Handle dc:identifier

https://hdl.handle.net/2142/132528

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/132528