Adaptive Anomaly Detection in Network Flows with Low-Rank Tensor Decompositions and Deep Unrolling

TL;DR

This paper introduces a novel deep unrolling-based anomaly detection method for network flows that models normal data as low-rank tensors and anomalies as sparse, achieving high efficiency, adaptability, and interpretability in critical communication systems.

Contribution

It proposes a new tensor decomposition and deep unrolling framework with online adaptation for anomaly detection in network flows, addressing data efficiency and domain adaptation challenges.

Findings

Outperforms existing methods on synthetic and real data.

Demonstrates high training data efficiency.

Seamlessly adapts to different network topologies.

Abstract

Anomaly detection (AD) is increasingly recognized as a key component for ensuring the resilience of future communication systems. While deep learning has shown state-of-the-art AD performance, its application in critical systems is hindered by concerns regarding training data efficiency, domain adaptation and interpretability. This work considers AD in network flows using incomplete measurements, leveraging a robust tensor decomposition approach and deep unrolling techniques to address these challenges. We first propose a novel block-successive convex approximation algorithm based on a regularized model-fitting objective where the normal flows are modeled as low-rank tensors and anomalies as sparse. An augmentation of the objective is introduced to decrease the computational cost. We apply deep unrolling to derive a novel deep network architecture based on our proposed algorithm, treating the regularization parameters as learnable weights. Inspired by Bayesian approaches, we extend the model architecture to perform online adaptation to per-flow and per-time-step statistics, improving AD performance while maintaining a low parameter count and preserving the problem's permutation equivariances. To optimize the deep network weights for detection performance, we employ a homotopy optimization approach based on an efficient approximation of the area under the receiver operating characteristic curve. Extensive experiments on synthetic and real-world data demonstrate that our proposed deep network architecture exhibits a high training data efficiency, outperforms reference methods, and adapts seamlessly to varying network topologies.