English

CyberCScope: Mining Skewed Tensor Streams and Online Anomaly Detection in Cybersecurity Systems

Machine Learning 2025-03-04 v1 Artificial Intelligence Cryptography and Security

Abstract

Cybersecurity systems are continuously producing a huge number of time-stamped events in the form of high-order tensors, such as {count; time, port, flow duration, packet size, . . . }, and so how can we detect anomalies/intrusions in real time? How can we identify multiple types of intrusions and capture their characteristic behaviors? The tensor data consists of categorical and continuous attributes and the data distributions of continuous attributes typically exhibit skew. These data properties require handling skewed infinite and finite dimensional spaces simultaneously. In this paper, we propose a novel streaming method, namely CyberCScope. The method effectively decomposes incoming tensors into major trends while explicitly distinguishing between categorical and skewed continuous attributes. To our knowledge, it is the first to compute hybrid skewed infinite and finite dimensional decomposition. Based on this decomposition, it streamingly finds distinct time-evolving patterns, enabling the detection of multiple types of anomalies. Extensive experiments on large-scale real datasets demonstrate that CyberCScope detects various intrusions with higher accuracy than state-of-the-art baselines while providing meaningful summaries for the intrusions that occur in practice.

Keywords

Cite

@article{arxiv.2503.00871,
  title  = {CyberCScope: Mining Skewed Tensor Streams and Online Anomaly Detection in Cybersecurity Systems},
  author = {Kota Nakamura and Koki Kawabata and Shungo Tanaka and Yasuko Matsubara and Yasushi Sakurai},
  journal= {arXiv preprint arXiv:2503.00871},
  year   = {2025}
}

Comments

Accepted by WWW 2025 short research paper

R2 v1 2026-06-28T22:03:37.441Z