Decoding BACnet Packets: A Large Language Model Approach for Packet Interpretation
This work addresses the problem of monitoring and securing ICS networks for SOC analysts, but it is incremental as it applies existing LLM and RAG methods to a new domain-specific protocol.
The paper tackled the challenge of interpreting complex Industrial Control System (ICS) communications, specifically BACnet packets, by developing a software solution using a Large Language Model (LLM) with Retrieval Augmented Generation (RAG) to generate clear summaries for Security Operations Center (SOC) analysts, enhancing their ability to assess network activities.
The Industrial Control System (ICS) environment encompasses a wide range of intricate communication protocols, posing substantial challenges for Security Operations Center (SOC) analysts tasked with monitoring, interpreting, and addressing network activities and security incidents. Conventional monitoring tools and techniques often struggle to provide a clear understanding of the nature and intent of ICS-specific communications. To enhance comprehension, we propose a software solution powered by a Large Language Model (LLM). This solution currently focused on BACnet protocol, processes a packet file data and extracts context by using a mapping database, and contemporary context retrieval methods for Retrieval Augmented Generation (RAG). The processed packet information, combined with the extracted context, serves as input to the LLM, which generates a concise packet file summary for the user. The software delivers a clear, coherent, and easily understandable summary of network activities, enabling SOC analysts to better assess the current state of the control system.