{"id":{"repo_id":"houston","oai_identifier":"oai:uh-ir.tdl.org:10657/20698"},"canonical_url":"https://search.dev.ndltd.org/etd/houston/oai:uh-ir.tdl.org:10657/20698","repository":{"repo_id":"houston","name":"University of Houston","base_url":"https://uh-ir.tdl.org/server/oai/request"},"display":{"title":"Teaching AIs to Reason and Code, Confidentially","abstract":"Large Language Models (LLMs) have advanced rapidly, creating new opportunities for automating complex software-engineering tasks, yet today’s models still produce semantically flawed code and raise safety, privacy, and lock-in concerns on centralized clouds. I present an end-to-end framework that teaches AI to reason about code and executes it on a decentralized, privacy-preserving infrastructure. At the modeling layer, I orchestrate a quorum of specialized LLM agents. A Director LLM coordinates a concept agent rooted in programming-language theory, language-specific experts, and a compiler-driven feedback loop. Implementations such as UniTranslator and Smartify deliver state-of-the-art translation, synthesis, and vulnerability repair, especially for low-resource domains like smart contracts. At the systems layer, I introduce DeFaaS, a blockchain-managed, multi-cloud Function-as-aService platform that removes single points of failure. I further prototype OGAIS, which enables trusted, on-device LLM inference triggered and verified by smart contracts, and I demonstrate zero-knowledge-proof workflows that preserve user privacy. To sustain performance, I repurpose Tensor Processing Units as cryptographic accelerators, cutting the latency of homomorphic encryption and zero-knowledge proofs by an order of magnitude. The resulting stack keeps every model invocation auditable while sensitive data stay encrypted. Together, these contributions advance AI-driven software engineering and establish a secure path for its deployment. By uniting reasoning-centric agents with verifiable, decentralized execution, this dissertation lays the groundwork for autonomous development tools that are demonstrably more accurate, transparent, and trustworthy.","abstract_html":"Large Language Models (LLMs) have advanced rapidly, creating new opportunities for automating complex software-engineering tasks, yet today’s models still produce semantically flawed code and raise safety, privacy, and lock-in concerns on centralized clouds. I present an end-to-end framework that teaches AI to reason about code and executes it on a decentralized, privacy-preserving infrastructure. At the modeling layer, I orchestrate a quorum of specialized LLM agents. A Director LLM coordinates a concept agent rooted in programming-language theory, language-specific experts, and a compiler-driven feedback loop. Implementations such as UniTranslator and Smartify deliver state-of-the-art translation, synthesis, and vulnerability repair, especially for low-resource domains like smart contracts. At the systems layer, I introduce DeFaaS, a blockchain-managed, multi-cloud Function-as-aService platform that removes single points of failure. I further prototype OGAIS, which enables trusted, on-device LLM inference triggered and verified by smart contracts, and I demonstrate zero-knowledge-proof workflows that preserve user privacy. To sustain performance, I repurpose Tensor Processing Units as cryptographic accelerators, cutting the latency of homomorphic encryption and zero-knowledge proofs by an order of magnitude. The resulting stack keeps every model invocation auditable while sensitive data stay encrypted. Together, these contributions advance AI-driven software engineering and establish a secure path for its deployment. By uniting reasoning-centric agents with verifiable, decentralized execution, this dissertation lays the groundwork for autonomous development tools that are demonstrably more accurate, transparent, and trustworthy.","abstract_has_math":false,"creators":["Karanjai, Rabimba 1989-"],"institution":"University of Houston","degree_name":"Doctor of Philosophy","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Shi, Weidong"],"committee_chairs":[],"committee_members":["Xu, Lei","Wu, Panruo","Huang, Shou-Hsuan Stephen"],"year":2025,"date_issued":"2025-08","date_published":"2025-08","updated_at":"2026-07-24T02:31:47Z","subjects":["Computer science"],"languages":["English"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10657/20698","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Shi, Weidong"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Xu, Lei","Wu, Panruo","Huang, Shou-Hsuan Stephen"]},{"key":"dc:creator","label":"Author","values":["Karanjai, Rabimba 1989-"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-10-06T19:39:59Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-08"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Houston"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["English"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10657/20698"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Large Language Models (LLMs) have advanced rapidly, creating new opportunities for automating complex software-engineering tasks, yet today’s models still produce semantically flawed code and raise safety, privacy, and lock-in concerns on centralized clouds. I present an end-to-end framework that teaches AI to reason about code and executes it on a decentralized, privacy-preserving infrastructure. At the modeling layer, I orchestrate a quorum of specialized LLM agents. A Director LLM coordinates a concept agent rooted in programming-language theory, language-specific experts, and a compiler-driven feedback loop. Implementations such as UniTranslator and Smartify deliver state-of-the-art translation, synthesis, and vulnerability repair, especially for low-resource domains like smart contracts. At the systems layer, I introduce DeFaaS, a blockchain-managed, multi-cloud Function-as-aService platform that removes single points of failure. I further prototype OGAIS, which enables trusted, on-device LLM inference triggered and verified by smart contracts, and I demonstrate zero-knowledge-proof workflows that preserve user privacy. To sustain performance, I repurpose Tensor Processing Units as cryptographic accelerators, cutting the latency of homomorphic encryption and zero-knowledge proofs by an order of magnitude. The resulting stack keeps every model invocation auditable while sensitive data stay encrypted. Together, these contributions advance AI-driven software engineering and establish a secure path for its deployment. By uniting reasoning-centric agents with verifiable, decentralized execution, this dissertation lays the groundwork for autonomous development tools that are demonstrably more accurate, transparent, and trustworthy."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Teaching AIs to Reason and Code, Confidentially"]}]}],"canonical_facts":{"dc:contributor.advisor":["Shi, Weidong"],"dc:contributor.committeemember":["Xu, Lei","Wu, Panruo","Huang, Shou-Hsuan Stephen"],"dc:creator":["Karanjai, Rabimba 1989-"],"dc:date.accessioned":["2025-10-06T19:39:59Z"],"dc:date.issued":["2025-08"],"dc:description.abstract":["Large Language Models (LLMs) have advanced rapidly, creating new opportunities for automating complex software-engineering tasks, yet today’s models still produce semantically flawed code and raise safety, privacy, and lock-in concerns on centralized clouds. I present an end-to-end framework that teaches AI to reason about code and executes it on a decentralized, privacy-preserving infrastructure. At the modeling layer, I orchestrate a quorum of specialized LLM agents. A Director LLM coordinates a concept agent rooted in programming-language theory, language-specific experts, and a compiler-driven feedback loop. Implementations such as UniTranslator and Smartify deliver state-of-the-art translation, synthesis, and vulnerability repair, especially for low-resource domains like smart contracts. At the systems layer, I introduce DeFaaS, a blockchain-managed, multi-cloud Function-as-aService platform that removes single points of failure. I further prototype OGAIS, which enables trusted, on-device LLM inference triggered and verified by smart contracts, and I demonstrate zero-knowledge-proof workflows that preserve user privacy. To sustain performance, I repurpose Tensor Processing Units as cryptographic accelerators, cutting the latency of homomorphic encryption and zero-knowledge proofs by an order of magnitude. The resulting stack keeps every model invocation auditable while sensitive data stay encrypted. Together, these contributions advance AI-driven software engineering and establish a secure path for its deployment. By uniting reasoning-centric agents with verifiable, decentralized execution, this dissertation lays the groundwork for autonomous development tools that are demonstrably more accurate, transparent, and trustworthy."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/10657/20698"],"dc:language.iso":["English"],"dc:subject":["Computer science"],"dc:title":["Teaching AIs to Reason and Code, Confidentially"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["Doctor of Philosophy"],"thesis:institution_name":["University of Houston"]},"updated_at":"2026-07-24T02:31:47Z"}