Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
Data Contract Virtual Machine (DC-VM): An Intelligent Governance Architecture for Reliable and Privacy-preserving AI Pipelines. |
| Συγγραφείς: |
Suresh, K., Suresh, Y., Aravindhan, Surendar, Kavitha, M., Karthika, J., Rajan, C. |
| Πηγή: |
International Journal of Intelligent Engineering & Systems; 2026, Vol. 19 Issue 1, p913-927, 15p |
| Θεματικοί όροι: |
Privacy, Data integrity, Artificial intelligence, Anomaly detection (Computer security), Legal compliance |
| Περίληψη: |
The problem of ensuring compliance with data integrity and privacy in multi-faceted pipelines of AI has become a pressing issue due to the implementation of heterogeneous machine learning pipelines across distributed systems by organizations. Traditional data governance implementations are based on static schema validation and human audit trails which do not offer runtime validation or cryptographic accountability. The proposed work is the Data Contract Virtual Machine (DC-VM), which is a programmable execution environment that implements data contracts based on policy all through AI dataflows. The DC-VM proposes a stratified validation system that combines deterministic rule programme execution and probabilistic anomaly detection to ensure that compliance and reliability are attained at every pipeline phase. To achieve end-to-end traceability, a lightweight proof-of-enforcement token allows revealing sensitive raw data. The prototype deployment shows that DC-VM is able to minimize incidents of contract-violation by 37 per cent and enhance throughput by 18 per cent over declarative governance frameworks. The findings substantiate the fact that executable contracts may be processed as high-level data structures of smart data infrastructures, which provide formal accountability, adaptive control, ad quantifiable resilience to data drift and privacy leakage. [ABSTRACT FROM AUTHOR] |
|
Copyright of International Journal of Intelligent Engineering & Systems is the property of Intelligent Networks & Systems Society and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Βάση Δεδομένων: |
Complementary Index |