Dependency-Based Link Prediction for Learning Microsegmentation Policy

Noel, Steven; Swarup, Vipin

doi:10.1007/978-3-031-15777-6_31

Cited by 1 publication

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The goal is to predict or disclose future or missing links between entities. Pope et al [25] proposed the use of tailored link prediction heuristics in this domain, while Noel and Swarup [26] used dependencybased link prediction for learning microsegmentation policies. It is worth noting that we are not aware of any work that would use this particular combination of the problem of device dependency detection and the approach of link prediction.…”

Section: Related Workmentioning

confidence: 99%

Identification of Device Dependencies Using Link Prediction

Sadlek,

Husák,

Čeleda

2024

NOMS 2024-2024 IEEE Network Operations and Management Symposium

View full text Add to dashboard Cite

Devices in computer networks cannot work without essential network services provided by a limited count of devices. Identification of device dependencies determines whether a pair of IP addresses is a dependency, i.e., the host with the first IP address is dependent on the second one. These dependencies cannot be identified manually in large and dynamically changing networks. Nevertheless, they are important due to possible unexpected failures, performance issues, and cascading effects. We address the identification of dependencies using a new approach based on graph-based machine learning. The approach belongs to link prediction based on a latent representation of the computer network's communication graph. It samples random walks over IP addresses that fulfill time conditions imposed on network dependencies. The constrained random walks are used by a neural network to construct IP address embedding, which is a space that contains IP addresses that often appear close together in the same communication chain (i.e., random walk). Dependency embedding is constructed by combining values for IP addresses from their embedding and used for training the resulting dependency classifier. We evaluated the approach using IP flow datasets from a controlled environment and university campus network that contain evidence about dependencies. Evaluation concerning the correctness and relationship to other approaches shows that the approach achieves acceptable performance. It can simultaneously consider all types of dependencies and is applicable for batch processing in operational conditions.

show abstract

Section: Related Workmentioning

confidence: 99%