In recent years, software ecosystems have become more complex with the proliferation of distributed systems such as blockchains and distributed ledgers. Effective management of these systems requires constant monitoring to identify any potential malfunctions, anomalies, vulnerabilities, or attacks. Traditional log auditing methods can effectively monitor the health of conventional systems. Yet, they run short of handling the higher levels of complexity of distributed systems. This study aims to propose an innovative architecture for system auditing that can effectively manage the complexity of distributed systems using advanced data analytics, natural language processing, and artificial intelligence.
To develop this architecture, we considered the unique characteristics of distributed systems and the various signals that may arise within them. We also felt the need for flexibility to capture these signals effectively. The resulting architecture utilizes advanced data analytics, natural language processing, and artificial intelligence to analyze and interpret the various signals emitted by the system.
We have implemented this architecture in the DELTA (Distributed Elastic Log Text Analyzer) auditing tool and applied it to the Hyperledger Fabric platform, a widely used implementation of private blockchains.
The proposed architecture for system auditing can effectively handle the complexity of distributed systems, and the DELTA tool provides a practical implementation of this approach. Further research could explore this approach's potential applications and effectiveness in other distributed systems.