Improved Flow Recovery from Packet Data

TL;DR

This paper discusses methods to accurately extract flow records from packet data, addressing current limitations and proposing improvements to enhance machine learning and cyber threat detection.

Contribution

It introduces novel techniques for more accurate and robust flow record extraction from packet data, along with proof of concept tools.

Findings

Improved accuracy in flow record extraction

Identification of limitations in current methods

Proposed methods enhance robustness and data quality

Abstract

Typical event datasets such as those used in network intrusion detection comprise hundreds of thousands, sometimes millions, of discrete packet events. These datasets tend to be high dimensional, stateful, and time-series in nature, holding complex local and temporal feature associations. Packet data can be abstracted into lower dimensional summary data, such as packet flow records, where some of the temporal complexities of packet data can be mitigated, and smaller well-engineered feature subsets can be created. This data can be invaluable as training data for machine learning and cyber threat detection techniques. Data can be collected in real-time, or from historical packet trace archives. In this paper we focus on how flow records and summary metadata can be extracted from packet data with high accuracy and robustness. We identify limitations in current methods, how they may impact datasets, and how these flaws may impact learning models. Finally, we propose methods to improve the state of the art and introduce proof of concept tools to support this work.