Adaptive DecayRank: Real-Time Anomaly Detection in Dynamic Graphs with Bayesian PageRank Updates
Real-time anomaly detection in large, dynamic graph networks is crucial for real-world applications such as network intrusion prevention, fraud transaction identification, fake news detection in social networks, and uncovering abnormal communication patterns. However, existing graph-based methods of...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/6/3360 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Real-time anomaly detection in large, dynamic graph networks is crucial for real-world applications such as network intrusion prevention, fraud transaction identification, fake news detection in social networks, and uncovering abnormal communication patterns. However, existing graph-based methods often focus on static graph structures, which struggle to adapt to the evolving nature of these graphs. In this paper, we propose <span style="font-variant: small-caps;">Adaptive-DecayRank</span>, a real-time and adaptive anomaly detection model for dynamic graph streams. Our method extends the dynamic PageRank algorithm by incorporating an adaptive Bayesian updating mechanism, allowing nodes to dynamically adjust their decay factors based on observed graph changes. This enables real-time detection of sudden structural shifts, improving anomaly identification in streaming graphs. We evaluate <span style="font-variant: small-caps;">Adaptive-DecayRank</span> on multiple real-world security datasets, including DARPA and CTU-13, as well as synthetic dense graphs generated using RTM. Our experiments demonstrate that <span style="font-variant: small-caps;">Adaptive-DecayRank</span> outperforms state-of-the-art methods, such as <span style="font-variant: small-caps;">AnomRank</span>, <span style="font-variant: small-caps;">Sedanspot</span>, and <span style="font-variant: small-caps;">DynAnom</span>, achieving up to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>13.94</mn><mo>%</mo></mrow></semantics></math></inline-formula> higher precision, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>8.43</mn><mo>%</mo></mrow></semantics></math></inline-formula> higher AUC, and more robust detection in highly dynamic environments. |
|---|---|
| ISSN: | 2076-3417 |