2025/06/06 by Yi Huang, Huang, Yi, Li, Shaofei +7
Computer Science · #Advanced Graph Neural Networks #Attack patterns #Cryptography and Security (cs.CR) #Entropy (arrow of time) #FOS: Computer and information sciences #Fidelity #Generalizability theory #Graph #Information and Cyber Security #Intrusion detection system #Network Security and Intrusion Detection #Semantics (computer science)
paper · pdf · doi:10.48550/arxiv.2506.06226
published in ArXiv.org
openalex publication_date 2025/06/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Provenance graph analysis plays a vital role in intrusion detection, particularly against Advanced Persistent Threats (APTs), by exposing complex attack patterns. While recent systems combine graph neural networks (GNNs) with natural language processing (NLP) to capture structural and semantic features, their effectiveness is limited by class imbalance in real-world data. To address this, we introduce PROVSYN, a novel hybrid provenance graph synthesis framework, which comprises three components: (1) graph structure synthesis via heterogeneous graph generation models, (2) textual attribute synthesis via fine-tuned Large Language Models (LLMs), and (3) five-dimensional fidelity evaluation. Experiments on six benchmark datasets demonstrate that PROVSYN consistently produces higher-fidelity graphs across the five evaluation dimensions compared to four strong baselines. To further demonstrate the practical utility of PROVSYN, we utilize the synthesized graphs to augment training datasets for downstream APT detection models. The results show that PROVSYN effectively mitigates data imbalance, improving normalized entropy by up to 35%, and enhances the generalizability of downstream detection models, achieving an accuracy improvement of up to 38%.