SynRAG: A Large Language Model Framework for Executable Query Generation in Heterogeneous SIEM System

TL;DR

SynRAG is a framework that automatically generates platform-specific SIEM queries from high-level specifications, enabling effective cross-platform threat detection and incident investigation in heterogeneous enterprise environments.

Contribution

We introduce SynRAG, a novel framework that translates platform-agnostic specifications into specific SIEM queries, improving cross-platform security operations and reducing manual effort.

Findings

SynRAG outperforms existing language models in generating effective SIEM queries.

It enables seamless threat detection across diverse SIEM platforms.

The framework reduces the need for extensive training on multiple SIEM systems.

Abstract

Security Information and Event Management (SIEM) systems are essential for large enterprises to monitor their IT infrastructure by ingesting and analyzing millions of logs and events daily. Security Operations Center (SOC) analysts are tasked with monitoring and analyzing this vast data to identify potential threats and take preventive actions to protect enterprise assets. However, the diversity among SIEM platforms, such as Palo Alto Networks Qradar, Google SecOps, Splunk, Microsoft Sentinel and the Elastic Stack, poses significant challenges. As these systems differ in attributes, architecture, and query languages, making it difficult for analysts to effectively monitor multiple platforms without undergoing extensive training or forcing enterprises to expand their workforce. To address this issue, we introduce SynRAG, a unified framework that automatically generates threat detection or incident investigation queries for multiple SIEM platforms from a platform-agnostic specification. SynRAG can generate platformspecific queries from a single high-level specification written by analysts. Without SynRAG, analysts would need to manually write separate queries for each SIEM platform, since query languages vary significantly across systems. This framework enables seamless threat detection and incident investigation across heterogeneous SIEM environments, reducing the need for specialized training and manual query translation. We evaluate SynRAG against state-of-the-art language models, including GPT, Llama, DeepSeek, Gemma, and Claude, using Qradar and SecOps as representative SIEM systems. Our results demonstrate that SynRAG generates significantly better queries for crossSIEM threat detection and incident investigation compared to the state-of-the-art base models.