LLMcap: Large Language Model for Unsupervised PCAP Failure Detection

TL;DR

This paper introduces LLMcap, a self-supervised large language model approach for detecting failures in Packet Capture data, improving network troubleshooting efficiency without requiring labeled datasets.

Contribution

The study presents a novel self-supervised LLM-based method for PCAP failure detection, leveraging language modeling techniques to handle unlabeled data effectively.

Findings

High accuracy in failure detection across various PCAP datasets

Effective use of masked language modeling for network data analysis

No labeled data needed for training, reducing resource requirements

Abstract

The integration of advanced technologies into telecommunication networks complicates troubleshooting, posing challenges for manual error identification in Packet Capture (PCAP) data. This manual approach, requiring substantial resources, becomes impractical at larger scales. Machine learning (ML) methods offer alternatives, but the scarcity of labeled data limits accuracy. In this study, we propose a self-supervised, large language model-based (LLMcap) method for PCAP failure detection. LLMcap leverages language-learning abilities and employs masked language modeling to learn grammar, context, and structure. Tested rigorously on various PCAPs, it demonstrates high accuracy despite the absence of labeled data during training, presenting a promising solution for efficient network analysis. Index Terms: Network troubleshooting, Packet Capture Analysis, Self-Supervised Learning, Large Language Model, Network Quality of Service, Network Performance.