Deep Learning for Anomaly Detection: A Survey (2019-01-10T00:00:00.000000Z)

TL;DR

A structured and comprehensive overview of research methods in deep learning-based anomaly detection, grouped state-of-the-art research techniques into different categories based on the underlying assumptions and approach adopted.

Abstract

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.

Authors

Raghavendra Chalapathy

1 papers

Sanjay Chawla

1 papers

TL;DR

Abstract

Authors

References477 items

DeepFall: Non-Invasive Fall Detection with Deep Spatio-Temporal Convolutional Autoencoders

Packet-data anomaly detection in PMU-based state estimator using convolutional neural network

Artificial Intelligence Crime: An Interdisciplinary Analysis of Foreseeable Threats and Solutions

Aircraft engine fault detection based on grouped convolutional denoising autoencoders

MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks

AlphaMEX: A smarter global pooling method for convolutional neural networks

Attentioned Convolutional LSTM InpaintingNetwork for Anomaly Detection in Videos

A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data

Estimation of Dimensions Contributing to Detected Anomalies with Variational Autoencoders

Multidimensional Time Series Anomaly Detection: A GRU-based Gaussian Mixture Variational Autoencoder Approach

MuVAN: A Multi-view Attention Network for Multivariate Temporal Data

Artificial intelligence in retina

Exploring Adversarial Examples in Malware Detection

MDGAN: Boosting Anomaly Detection Using Multi-Discriminator Generative Adversarial Networks

Generative Ensembles for Robust Anomaly Detection

WAIC, but Why? Generative Ensembles for Robust Anomaly Detection

Flow-based Network Traffic Generation using Generative Adversarial Networks

Exploring the interpretability of LSTM neural networks over multi-variable data

Deep Learning Approach Combining Sparse Autoencoder With SVM for Network Intrusion Detection

Long-term temporal averaging for stochastic optimization of deep neural networks

Toward Sustainable Virtualized Healthcare: Extracting Medical Entities from Chinese Online Health Consultations Using Deep Neural Networks

Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series

Deep learning for time series classification: a review

Host Based Intrusion Detection System with Combined CNN/RNN Model

Image Anomaly Detection with Generative Adversarial Networks

BINet: Multivariate Business Process Anomaly Detection Using Deep Learning

VOS: a Method for Variational Oversampling of Imbalanced Data

Semi-Supervised Outlier Detection Using a Generative and Adversary Framework

Anomaly Detection in Moving Crowds through Spatiotemporal Autoencoding and Additional Attention

Zero-day malware detection using transferred generative adversarial networks based on deep autoencoders

Evaluation of deep learning approaches based on convolutional neural networks for corrosion detection

Scalable Deep Learning through Fuzzy-Based Clustering in Autonomous Systems

MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks

Using convolutional neural networks for classification of malware represented as images

An investigation of a deep learning based malware detection system

DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN

Enhanced Network Anomaly Detection Based on Deep Neural Networks

A Model Based on Convolutional Neural Network for Online Transaction Fraud Detection

A deep Recurrent Neural Network based approach for Internet of Things malware threat hunting

A Combined Deep Learning GRU-Autoencoder for the Early Detection of Respiratory Disease in Pigs Using Multiple Environmental Sensors

Credit Card Fraud Detection Based on Whale Algorithm Optimized BP Neural Network

A Survey of Anomaly Detection in Industrial Wireless Sensor Networks with Critical Water System Infrastructure as a Case Study

Detecting Anomaly in Big Data System Logs Using Convolutional Neural Network

Semi-Supervised Generative Adversarial Network for Gene Expression Inference

Are generative deep models for novelty detection truly better?

When deep learning meets security

Automatic Rumor Detection on Microblogs: A Survey

Spatio-Temporal Network Traffic Estimation and Anomaly Detection Based on Convolutional Neural Network in Vehicular Ad-Hoc Networks

Recurrent Neural Networks for Enhancement of Signature-based Network Intrusion Detection Systems

AND: Autoregressive Novelty Detectors

Deep One-Class Classification

Anomaly Detection for Skin Disease Images Using Variational Autoencoder

Deep learning at the shallow end: Malware classification for non-domain experts

A Deep Learning-Based Method for Sleep Stage Classification Using Physiological Signal

Anomaly Machine Component Detection by Deep Generative Model with Unregularized Score

A review on the application of deep learning in system health management

Time Series Prediction and Anomaly Detection of Light Curve Using LSTM Neural Network

Malware Detection in Cloud Infrastructures Using Convolutional Neural Networks

Toward Explainable Deep Neural Network Based Anomaly Detection

An Empirical Study on Network Anomaly Detection Using Convolutional Neural Networks

LiReD: A Light-Weight Real-Time Fault Detection System for Edge Computing Using LSTM Recurrent Neural Networks

Neural Network Cognitive Engine for Autonomous and Distributed Underlay Dynamic Spectrum Access

A Review of Artificial Intelligence Algorithms Used for Smart Machine Tools

Desh: deep learning for system health prediction of lead times to failure in HPC

Insider Threat Detection with Deep Neural Network

SU-IDS: A Semi-supervised and Unsupervised Framework for Network Intrusion Detection

Probabilistic Deep Learning using Random Sum-Product Networks

DeepAD: A Generic Framework Based on Deep Learning for Time Series Anomaly Detection

Generative adversarial network based telecom fraud detection at the receiving bank

Outlier Detection for Multidimensional Time Series Using Deep Neural Networks

Unsupervised Anomaly Detection for Traffic Surveillance Based on Background Modeling

Sequence classification for credit-card fraud detection

Anomaly Detection for Short Texts: Identifying Whether Your Chatbot Should Switch from Goal-Oriented Conversation to Chit-Chatting

Semi-supervised Encoding for Outlier Detection in Clinical Observation Data

An enhancing framework for botnet detection using generative adversarial networks

A hybrid deep learning model for consumer credit scoring