Anomaly Detection in Time Series of Graphs using Fusion of Graph Invariants

@article{Park2013AnomalyDI,
  title={Anomaly Detection in Time Series of Graphs using Fusion of Graph Invariants},
  author={Youngser Park and Carey E. Priebe and Abdou Youssef},
  journal={IEEE Journal of Selected Topics in Signal Processing},
  year={2013},
  volume={7},
  pages={67-75}
}
Given a time series of graphs <i>G</i>(<i>t</i>)=(<i>V</i>,<i>E</i>(<i>t</i>)) , <i>t</i>=1,2,... , where the fixed vertex set <i>V</i> represents “actors” and an edge between vertex <i>u</i> and vertex <i>v</i> at time <i>t</i>(<i>uv</i> ∈ <i>E</i>(<i>t</i>)) represents the existence of a communications event between actors <i>u</i> and <i>v</i> during the <i>t</i><sup>th</sup> time period, we wish to detect anomalies and/or change points. We consider a collection of graph features, or… 
Multiple Network Embedding for Anomaly Detection in Time Series of Graphs.
TLDR
Applied to a large-scale commercial search engine time series of graphs, the adaptation of statistically principled methods for joint graph inference, specifically multiple adjacency spectral embedding and omnibus embedding are demonstrated to be applicability and identify the anomalous vertices beyond just large degree change.
Anomaly Detection With Subgraph Search and Vertex Classification Preprocessing in Chung-Lu Random Networks
TLDR
Two preprocessing approaches are developed, referred to as subgraph search and vertex classification, and two detection algorithms are proposed which can be applicable to the generalized network model (Chung-Lu random graph), which can achieve better detection performance than the existing algorithms.
Locality Statistics for Anomaly Detection in Time Series of Graphs
TLDR
This paper formulates change-point detection as a hypothesis testing problem in terms of a generative latent position model, focusing on the special case of the Stochastic Block Model time series.
Change detection in dynamic attributed networks
  • I. Hewapathirana
  • Computer Science, Mathematics
    Wiley Interdiscip. Rev. Data Min. Knowl. Discov.
  • 2019
TLDR
An overview of some of the existing change detection methods that utilize attribute information is provided, based on the levels of structure in the graph that are exploited to detect changes, including vertices, edges, subgraphs, communities, and the overall graph.
Anomaly Detection in Dynamic Networks
Anomaly detection in dynamic communication networks has many important security applications. These networks can be extremely large and so detecting any changes in their structure can be
Attribute Fusion in a Latent Process Model for Time Series of Graphs
TLDR
Inferential performance in mathematically tractable first-order and second-order approximation models does provide guidance for methodological choices applicable to the exact model, and it is tentatively concluded that approximation model investigations have some bearing on real data applications.
Nonparametric Anomaly Detection on Time Series of Graphs
TLDR
This work proposes a distribution-free framework for anomaly detection in dynamic networks and adopts a change point detection method for (weakly) dependent time series based on efficient scores, and enhances the finite sample properties of change point method by approximating the asymptotic distribution of the test statistic using the sieve bootstrap.
Nonparametric Anomaly Detection on Time Series of Graphs
TLDR
This work proposes a distribution-free framework for anomaly detection in dynamic networks and adopts a change point detection method for (weakly) dependent time series based on efficient scores, and enhances the finite sample properties of change point method by approximating the asymptotic distribution of the test statistic using the sieve bootstrap.
Sim-Watchdog: Leveraging Temporal Similarity for Anomaly Detection in Dynamic Graphs
  • Guanhua Yan, S. Eidenbenz
  • Computer Science
    2014 IEEE 34th International Conference on Distributed Computing Systems
  • 2014
TLDR
This work proposes a systematic framework that leverages temporal similarity inherent in dynamic graphs for anomaly detection that relies on the Neyman-Pearson criterion to choose similarity measures with high discriminative power for online anomaly detection inynamic graphs.
Detecting changes in transient complex systems via dynamic network inference
TLDR
An approach to detecting changes in complex dynamic systems that is based on spectral-graph-theory and uses a single realization of time series data collected under specific, common types of transient conditions, such as intermittency is presented.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 24 REFERENCES
Anomaly detection for random graphs using distributions of vertex invariants
TLDR
A novel method of incorporating information from vertex invariants for anomaly detection on graphs, a principled approach to fusing information from an arbitrary number of such statistics, and superior performance to available state-of-the-art approaches are demonstrated.
Eigenspace-based anomaly detection in computer systems
TLDR
It is demonstrated that a fault in a Web application can be automatically detected and the faulty services are identified without using detailed knowledge of the behavior of the system.
Scan Statistics for the Online Detection of Locally Anomalous Subgraphs
We introduce a computationally scalable method for detecting small anomalous areas in a large, time-dependent computer network, motivated by the challenge of identifying intruders operating inside
Attribute Fusion in a Latent Process Model for Time Series of Graphs
TLDR
Inferential performance in mathematically tractable first-order and second-order approximation models does provide guidance for methodological choices applicable to the exact model, and it is tentatively concluded that approximation model investigations have some bearing on real data applications.
Changepoint Detection over Graphs with the Spectral Scan Statistic
TLDR
A tractable relaxation of the GLR statistic is developed based on the combinatorial Laplacian of the graph, which is called the spectral scan statistic, and its properties are analyzed.
Adaptive graph-based algorithms for conditional anomaly detection and semi-supervised learning
TLDR
A fast approximate online algorithm that solves for the harmonic solution on an approximate graph and shows, both empirically and theoretically, that good behavior can be achieved by collapsing nearby points into a set of local representative points that minimize distortion.
Matched filtering for subgraph detection in dynamic networks
Graphs are high-dimensional, non-Euclidean data, whose utility spans a wide variety of disciplines. While their non-Euclidean nature complicates the application of traditional signal processing
The phase transition in inhomogeneous random graphs
We introduce a very general model of an inhomogenous random graph with independence between the edges, which scales so that the number of edges is linear in the number of vertices. This scaling
Statistical inference on attributed random graphs: Fusion of graph features and content: An experiment on time series of Enron graphs
TLDR
An experiment on a time series of attributed graphs extracted from the Enron email corpus which demonstrates the benefit of fusion, based on injecting a controlled anomaly into the real data and measuring its detectability.
Online anomaly detection with expert system feedback in social networks
  • Corinne Horn, R. Willett
  • Computer Science
    2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2011
In this paper, we propose examining the participants in various meetings or communications within a social network, and using sequential inference based on these participant lists to quickly and
...
1
2
3
...