My research focuses on distributed systems based on the CAP theorem, examining the trade-offs among consistency, availability, and partition tolerance. Specifically, I study consensus algorithms such as Paxos, PBFT, PoW, and PoS, as well as supporting mechanisms including hash functions, digital signatures, Rollup technologies represented by Arbitrum, and cryptographic techniques such as zk-SNARKs that prove the correctness of computations without revealing their intermediate processes. Through the integrated analysis of these technologies, I aim to design distributed consensus infrastructures that achieve both reliability and scalability.

I conduct research on mechanisms that enable third parties to reproduce and verify the outputs and decision-making processes of AI systems. This includes designing methods to validate the behavior, reasoning, and data integrity of AI agents, while extending the concepts of Explainable AI and Auditable AI. By integrating these approaches with distributed infrastructures such as blockchains and dataspaces, my research aims to enhance the transparency, reliability, and reproducibility of AI.

I conduct research on mechanisms that ensure trustworthiness and accountability in data sharing and utilization. Building upon Usage Control and Access Control, my work integrates cryptographic technologies, hardware-based trust foundations such as Trusted Platform Modules (TPM), and quantum entanglement–based verification of data-opening procedures to establish governance mechanisms that enable auditability and verifiability throughout the entire data lifecycle—from generation to utilization.

I develop formal models to describe and analyze the behavior of consensus systems, verifiable AI, and data governance mechanisms in terms of reliability, performance, and scalability. Through mathematical modeling, my research seeks to clarify the theoretical design principles underlying distributed systems and dataspaces.