Graph-based anomaly detection

By Caleb C. Noble, Diane Joyce Cook. Knowledge Discovery and Data Mining, 2003

577 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/863efef58318bdc21986470200f6d4f2d206e039

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

In Statistical and Nonlinear Physics

Citations in the corpus

Anomaly detection in online social networks (2014, background): “…(Shetty and Adibi, 2005; Tsugawa et al., 2010; Serin and Balcisoy, 2012), or may represent a normal pattern of behaviour that can then be used as a point of comparison, with those subgraphs that deviate from this norm considered to be anomalous (Noble and Cook, 2003; Eberle and Holder, 2007, 2009).”
Neighborhood formation and anomaly detection in bipartite graphs (2005, background): “Noble and Cook [13] study anomaly detection on general graph with labeled nodes; yet, their goal is to identify abnormal substructure in the graph, not the abnormal nodes.”
Fast Memory-efficient Anomaly Detection in Streaming Heterogeneous Graphs (2016, methodology): “Those for typed or attributed graphs aim to find deviations from frequent substructures [27, 12, 23], anomalous subgraphs [17, 29], and community outliers [14, 30], all of which are designed for static graphs.”
You Are What You Do: Hunting Stealthy Malware via Data Provenance Analysis (2020, methodology): “Anomaly Detection with Host Level System Events Several approaches have been proposed to detect intrusion or abnormal behaviors using system event data on the end hosts [74], [75], [36], [22], [14].”
It's who you know: graph mining using recursive structural features (2011, background): “Another body of related work uses frequent sub-graphs as structural features for classification of graphs [18, 8] and anomaly detection [26, 22].”
A Comprehensive Survey on Graph Anomaly Detection With Deep Learning (2021, methodology): “Due to the complexity of anomaly detection and graph data mining [63], [64], [65], [66], [67], in addition to the prior mentioned data-speciﬁc challenges, adopting deep learning techniques for graph anomaly detection also faces a number of challenges from the technical side.”
Anomaly detection in dynamic networks: a survey (2015, methodology): “These techniques complement methods for static graphs [59, 27, 26, 6], as the latter cannot be easily adopted for dynamic networks.”
Outlier Analysis (2013, methodology): “The approach proposed in [349] is based on the Minimum Description Length (MDL) principle for outlier detection.”
Local Modeling of Attributed Graphs: Algorithms and Applications (2016, methodology): “In their seminal work, Noble and Cook [110] used frequent subgraph mining and information theoretic principles to identify anomalous subgraphs in graphs with a single attribute.”
A survey of network anomaly detection techniques (2016, background): “Noble and Cook (2003) conducted experiments on the benchmark DARPA and UNM audit datasets to demonstrate the utility of information-theoretic measures and concluded that they can be used to create efficient anomaly detection models and also to explain their performances.”
A Unifying Review of Deep and Shallow Anomaly Detection (2020, background): “Other examples include spatial [205], [206], spatiotemporal [192], or graph-based [171], [207], [208] anomalies.”
Effective Pattern Discovery for Text Mining (2012, background): “Cook (2003)[16] focused on anomaly detection in graph based data.”
Rethinking Graph Neural Networks for Anomaly Detection (2022, background): “Consequently, as a crucial research direction, graph-based anomaly detection is necessary to be further explored (Noble & Cook, 2003; Ma et al., 2021).”
Unsupervised Anomaly Detection in Network Intrusion Detection Using Clusters (2005, methodology): “One approach uses graphs for modelling the normal data and detect the irregularities in the graph for anomalies (Noble & Cook 2003).”
oddball: Spotting Anomalies in Weighted Graphs (2010, methodology): “Noble and Cook [26] detect anomalous sub-graphs using variants of the Minimum Description Length (MDL) principle.”