Enhancing Graph-Based Advanced Persistent Threat Detection with LLM Sentence Embedding
- 12 November 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1238-1243
Abstract
Advanced Persistent Threat (APT) attacks represent a sophisticated and growing danger to modern information systems. While provenance graphs are a promising tool for detecting these complex threats, their effectiveness is often limited by a failure to harness the rich semantic information contained within raw system logs. This paper proposes a novel detection framework that addresses this gap by leveraging a Large Language Model (LLM) to embed deep semantic meaning from system logs directly into the graph's features. Our approach enhances a state-of-the-art Graph Neural Network (GNN)-based method by replacing its simple embedding technique with an LLM-based sentence embedding method, specifically enriching the graph's edge features to capture deeper contextual information. Experimental results on the challenging Unicorn Wget dataset demonstrate the superiority of our method. It surpassed the baseline in all evaluation metrics, achieving an F1-Score of 96.12 % and an AUC of 98.52 %, compared to the baseline's 94.36 % F1-Score and 97.39% AUC. Furthermore, our method achieved a lower false positive rate of 6.68 %, indicating a more precise and reliable detection capability. These findings highlight the value of integrating semantic embeddings from LLMs to improve the detection of stealthy, complex cyberattacks.Keywords
Funding Information
- JSPS (25K21210)
This publication has 10 references indexed in Scilit:
- Training-free retrieval-based log anomaly detection with pre-trained language model considering token-level informationEngineering Applications of Artificial Intelligence, 2024
- Flash: A Comprehensive Approach to Intrusion Detection via Provenance Graph Representation Learning2024
- LAnoBERT: System log anomaly detection based on BERT masked language modelApplied Soft Computing, 2023
- GraphMAE: Self-Supervised Masked Graph Autoencoders2022
- Log-based Anomaly Detection Without Log Parsing2021
- LogBERT: Log Anomaly Detection via BERT2021
- Tactical Provenance Analysis for Endpoint Detection and Response Systems2020
- You Are What You Do: Hunting Stealthy Malware via Data Provenance Analysis2020
- POIROT2019
- Practical whole-system provenance capture2017