Anomaly detection: A survey

By Varun Chandola, Arindam Banerjee, Vipin Kumar. 2009

12,600 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Safety, Robustness & Interpretability

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 Safety, Robustness & Interpretability

Citations in the corpus

A Survey of Machine Learning for Big Code and Naturalness (2017, methodology): “This is analogous to anomaly detection using machine learning [39].”
Strike (With) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects (2018, methodology): “augmenting the training set with AXs—also a common approach in anomaly detection [9].”
DeepWalk: online learning of social representations (2014, background): “ommendation [11], anomaly detection [5], and missing link prediction [22]) must be able to deal with this sparsity in order to survive.”
Towards the Science of Security and Privacy in Machine Learning (2016, methodology): “For instance, clustering may be applied to anomaly detection [11].”
Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift (2018, methodology): “Given just one example from the test data, our problem simpliﬁes to anomaly detection , surveyed thoroughly by Chandola et al. [8] and Markou and Singh [33].”
One-Class Support Measure Machines for Group Anomaly Detection (2013, methodology): “The anomaly detection has been intensively studied (Chandola et al. (2009) and references therein).”
Nonparametric Divergence Estimation with Applications to Machine Learning on Distributions (2011, background): “The standard anomaly/novelty detection methods only focus on ﬁnding individual points (Chandola et al., 2009).”
SoK: Security and Privacy in Machine Learning (2018, methodology): “For instance, clustering may be applied to anomaly detection [12].”
Learning Placeholders for Open-Set Recognition (2021, background): “The problem of out-ofdistribution detection [10, 17, 1], anomaly detection [4, 18, 25] and novelty detection [11, 32, 41, 21, 43] are related topics to open-set recognition.”
Neural Trojans (2017, methodology): “The anomaly detection [7] methods used here include support vector machines (SVMs) and decision trees (DTs).”
A least-squares approach to anomaly detection in static and sequential data (2014, methodology): “There are many existing methods for anomaly detection, for which an extensive review can be found in Chandola et al. (2009).”
A Comprehensive Survey on Graph Anomaly Detection With Deep Learning (2021, background): “There are some representative surveys on generalized anomaly detection techniques - [18], [45] and [44].”
Local Modeling of Attributed Graphs: Algorithms and Applications (2016, background): “Machine learning applications in networks (such as network classification [53, 125], content recommendation [46], anomaly detection [27], and missing link prediction [80]) must be able to deal with this sparsity in order to survive.”
Experience Report: System Log Analysis for Anomaly Detection (2016, methodology): “[14] survey anomaly detection methods that use machine learning techniques in different categories, but this paper aims at reviewing and benchmarking the existing work that applies log analysis techniques to system anomaly detection.”
GOTCHA! Network-Based Fraud Detection for Social Security Fraud (2017, background): “The aforementioned problems generally exhibit the same characteristics, but the solution to each problem is rather domain-specific (Chandola et al. 2009).”
Learning Graph Representations with Embedding Propagation (2017, background): “The computational problems commonly addressed in these domains are network classiﬁcation [40], statistical relational learning [12, 36], link prediction [22, 24], and anomaly detection [8, 1], to name but a few.”
Outlier Analysis (2013, background): “Among these, the survey by Chandola et al [107], is the most recent, and arguably the most comprehensive.”
One-class classification: taxonomy of study and review of techniques (2013, neutral): “1 Readers are advised to refer to detailed literature survey on outlier detection by Chandola et al. (2009). 2 Readers are advised to refer to detailed literature survey on novelty detection by Markou and Singh (2003a, 2003b).”