Deep Learning for Anomaly Detection: A Survey

By Raghavendra Chalapathy, Sanjay Chawla. arXiv.org, 2019

1,857 citations recorded by the source corpus.

Anomaly detection is an important problem that has been well-studied within diverse research areas and application domains. The aim of this survey is two-fold, firstly we present a structured and comprehensive overview of research methods in deep learning-based anomaly detection. Furthermore, we review the adoption of these methods for anomaly across various application domains and assess their effectiveness. We have grouped state-of-the-art research techniques into different categories based on the underlying assumptions and approach adopted. Within each category we outline the basic anomaly detection technique, along with its variants and present key assumptions, to differentiate between normal and anomalous behavior. For each category, we present we also present the advantages and limitations and discuss the computational complexity of the techniques in real application domains. Finally, we outline open issues in research and challenges faced while adopting these techniques.

Subfields: Artificial Intelligence, Computer Networks and Communications, Signal Processing

View Paper: https://www.semanticscholar.org/paper/a2e667e4382aaa8e02a17d0522c1a910790ab65b

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 Signal Processing

Citations in the corpus

A Survey on Machine Learning Techniques for Cyber Security in the Last Decade (2020, background): “Some papers summarized intrusion detection techniques and ML techniques in detail [3], [73], [77], [398]–[406].”
Cellular, Wide-Area, and Non-Terrestrial IoT: A Survey on 5G Advances and the Road Toward 6G (2021, methodology): “DL techniques, including AE-based ones, have been proposed to address security threats such as anomaly and intrusion detection in IoT networks [311].”
A Comprehensive Survey on Graph Anomaly Detection With Deep Learning (2021, background): “Recognizing the power of deep learning, the three contemporary surveys, Ruff et al. [71], Pang et al. [24] and Chalapathy and Chawla [47] specifically review deep learning based anomaly detection techniques speciﬁcally.”
Deep Learning for Time Series Anomaly Detection: A Survey (2022, neutral): “Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page.”
Deep Learning for Medical Anomaly Detection – A Survey (2020, background): “One of the main challenges arises from the inconsistent behaviour of different anomalies, and the lack of constant definition of what constitutes an anomaly [1], [2], [3].”
USAD: UnSupervised Anomaly Detection on Multivariate Time Series (2020, background): “Detecting unexpected behavior on a set of measurements correlated with each other over time is an active research discipline called anomaly detection in multivariate time series [2].”
Anomaly Detection for IoT Time-Series Data: A Survey (2020, methodology): “When deploying an anomaly detection method into a new or poorly known system it is often impossible to provide a sufﬁcient historic data set to be able to correctly deﬁne both the normal operating state of the system as well as any or all potential anomaly types which may be seen [42].”
Trustworthy AI: From Principles to Practices (2021, methodology): “Various approaches have been proposed to address this issue by using anomaly detection [70].”
Progress in Outlier Detection Techniques: A Survey (2019, methodology): “In deep OD methods, based on the training objectives, these methods can employ Deep Hybrid Models (DHM) or One Class Neural Networks (OCNN) [32].”
Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis, and Guidelines (2021, background): “To the best of our knowledge, previous reviews [1], [2], [9]–[14] on this subject matter do no more than simply categorize models according to their mechanisms and describe their characteristics.”
LogBERT: Log Anomaly Detection via BERT (2021, methodology): “Therefore, it is suboptimal to train a binary classifier for log anomaly detection [7].”
Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals (2021, methodology): “ANOMALY detection has been one of the core research areas in machine learning for decades, with wide applications such as cyber-intrusion detection [1], medical care [2], sensor networks [3], video anomaly detection [4] and so”
Deep Anomaly Detection for Time-Series Data in Industrial IoT: A Communication-Efficient On-Device Federated Learning Approach (2020, background): “In statistics, anomalies (also called outliers and abnormalities) are the data points that are significantly different from other observations [11].”
Time Series Data Augmentation for Deep Learning: A Survey (2020, background): “, 2019], and time series anomaly detection [Chalapathy and Chawla, 2019].”
TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data (2022, background): “Moreover, the lack of labeled data and anomaly diversity makes the problem challenging as we cannot use supervised learning models, which have shown to be effective in other areas of data mining [12].”
HRN: A Holistic Approach to One Class Learning (2020, methodology): “More details about these applications and others can be found in the recent survey [7, 61].”
Anomaly Detection in Time Series: A Comprehensive Evaluation (2022, background): “The different anomaly types, pattern models, and time series properties led to the development of amultitude of different anomaly detection algorithms, about which various surveys exist [12, 20, 27, 28, 29, 37, 38, 53, 63].”