{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/129192"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/129192","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Assessing trustworthiness of neural networks for computer systems","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","abstract_has_math":false,"creators":["Chaudhary, Isha"],"institution":"University of Illinois Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Singh, Gagandeep"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-04-11","date_published":"2025-04-11","updated_at":"2026-07-22T22:25:04Z","subjects":["Neural Networks","Computer Systems","Formal Methods"],"languages":["en","eng"],"rights":["Copyright 2025 Isha Chaudhary"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/129192","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Singh, Gagandeep"]},{"key":"dc:creator","label":"Author","values":["Chaudhary, Isha"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-04-11","2025-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Neural Networks","Computer Systems","Formal Methods"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2025 Isha Chaudhary"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/129192"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","The student, Isha Chaudhary, accepted the attached license on 2025-04-10 at 12:44.","The student, Isha Chaudhary, submitted this Thesis for approval on 2025-04-10 at 12:48.","This Thesis was approved for publication on 2025-04-11 at 09:40.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21740 on 2025-10-19 at 18:09:18","Neural networks have exhibited superior performance in several domains such as computer vision, natural language processing, etc. They have also been trained as computer system components for performance improvement. Although they deliver expected performance, they are not trusted by domain experts, as they are black-box functions and can show unexpected behaviors. This is particularly important for computer systems, as any unpredictable errors in one component can lead to catastrophic failure of the entire system, which is often deployed in consumer-facing applications. Hence, it becomes imperative to develop custom methods to evaluate and develop trust in neural network components of computer systems. In this thesis, I will describe a couple of frameworks that I have developed to address the issue of trust of neural networks in computer systems. The first framework, COMET, is an explanation framework to generate faithful explanations for the predictions of neural networks deployed as performance/cost models in compilers. Cost models statically predict the cost of execution of a given piece of code on a specific CPU. Their predictions are used to direct the compiler optimizations towards the most effective transformations of the code, hence making them crucial for effective compilation. Recent research has developed neural cost models. However, they are not considered trustworthy, as they are black-boxes with no insight into what led to their predictions. Our framework, COMET, is the first step towards mitigating this concern. COMET generates explanations for the prediction of any given cost model for an input code, as a subset of the features of the code that are sufficient to result in the prediction. With explanations, incorrect behaviors of the black-box cost models can be debugged and the trust of the domain experts can be achieved. The second framework, SpecTRA is an automated specification generation system for neural networks as computer system components. We formulate specification generation as an optimization problem and solve it with observations of expected behaviors. We hypothesize that the traditional (aka reference) algorithms that neural networks replace for higher performance can act as effective proxies for expected correct behaviors of the models, when available. SpecTRA clusters similar observations into compact specifications. We present specifications generated by SpecTRA for neural networks in adaptive bit rate and congestion control algorithms. Our specifications show evidence of being correct and matching intuition. Moreover, we use our specifications to show several previously unknown vulnerabilities in SOTA neural models for computer systems."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Assessing trustworthiness of neural networks for computer systems"]}]}],"canonical_facts":{"dc:contributor":["Singh, Gagandeep"],"dc:creator":["Chaudhary, Isha"],"dc:date":["2025-04-11","2025-05"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms","The student, Isha Chaudhary, accepted the attached license on 2025-04-10 at 12:44.","The student, Isha Chaudhary, submitted this Thesis for approval on 2025-04-10 at 12:48.","This Thesis was approved for publication on 2025-04-11 at 09:40.","DSpace SAF Submission Ingestion Package generated from Vireo submission #21740 on 2025-10-19 at 18:09:18","Neural networks have exhibited superior performance in several domains such as computer vision, natural language processing, etc. They have also been trained as computer system components for performance improvement. Although they deliver expected performance, they are not trusted by domain experts, as they are black-box functions and can show unexpected behaviors. This is particularly important for computer systems, as any unpredictable errors in one component can lead to catastrophic failure of the entire system, which is often deployed in consumer-facing applications. Hence, it becomes imperative to develop custom methods to evaluate and develop trust in neural network components of computer systems. In this thesis, I will describe a couple of frameworks that I have developed to address the issue of trust of neural networks in computer systems. The first framework, COMET, is an explanation framework to generate faithful explanations for the predictions of neural networks deployed as performance/cost models in compilers. Cost models statically predict the cost of execution of a given piece of code on a specific CPU. Their predictions are used to direct the compiler optimizations towards the most effective transformations of the code, hence making them crucial for effective compilation. Recent research has developed neural cost models. However, they are not considered trustworthy, as they are black-boxes with no insight into what led to their predictions. Our framework, COMET, is the first step towards mitigating this concern. COMET generates explanations for the prediction of any given cost model for an input code, as a subset of the features of the code that are sufficient to result in the prediction. With explanations, incorrect behaviors of the black-box cost models can be debugged and the trust of the domain experts can be achieved. The second framework, SpecTRA is an automated specification generation system for neural networks as computer system components. We formulate specification generation as an optimization problem and solve it with observations of expected behaviors. We hypothesize that the traditional (aka reference) algorithms that neural networks replace for higher performance can act as effective proxies for expected correct behaviors of the models, when available. SpecTRA clusters similar observations into compact specifications. We present specifications generated by SpecTRA for neural networks in adaptive bit rate and congestion control algorithms. Our specifications show evidence of being correct and matching intuition. Moreover, we use our specifications to show several previously unknown vulnerabilities in SOTA neural models for computer systems."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/129192"],"dc:language":["en","eng"],"dc:rights":["Copyright 2025 Isha Chaudhary"],"dc:subject":["Neural Networks","Computer Systems","Formal Methods"],"dc:title":["Assessing trustworthiness of neural networks for computer systems"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:04Z"}