Provenance-Based Cybersecurity for LLMs Using Lossless Graph Compression for Computational Efficiency
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Provenance-based cybersecurity enables auditability and integrity in artificial intelligence systems but introduces substantial computational overhead, particularly for large language model (LLM) pipelines. Existing provenance compression approaches often sacrifice fidelity or lack demonstrable scalability. This paper presents CompProGraph, a two-stage lossless provenance compression framework that combines structural signature hashing with format-preserving JSON packing to reduce redundancy while preserving full W3C PROV semantics.Using the OpenML℄CC18 benchmark as a structural proxy for LLM-like provenance workflows, CompProGraph achieves consistent storage reductions of approximately 59% with linear-time compression and decompression. We further evaluate scalability on extended provenance corpora derived from repeated execution templates, ranging from megabytes to multi-gigabyte scale, demonstrating linear runtime and stable memory growth as corpus size increases by orders of magnitude.Although CC18 does not capture all semantic and temporal properties of real LLM pipelines, these results provide empirical evidence that exploiting structural similarity enables efficient, lossless provenance compression at scale. CompProGraph thus represents a practical step toward scalable and audit-ready provenance systems for trustworthy and compliant AI deployments.
Fields of Study & Subjects
Scientific Computing and Data Management
Explainable Artificial Intelligence (XAI)
Access Control and Trust
Publication details
- Journal / source
- IEEE Transactions on Artificial Intelligence
- Pages
- 1–10
- Publication date
- 1 January 2026
- Language
- EN