Deep Learning for Anomaly Detection: A Survey

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.

References in corpus (68)

• Deep Learning in Neural Networks: An Overview
• A Survey on Deep Learning in Medical Image Analysis
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Deep learning for time series classification: a review
• Convolutional Neural Networks for Sentence Classification
• Zero-Shot Learning Through Cross-Modal Transfer
• Efficient GAN-Based Anomaly Detection
• Unsupervised and Semi-supervised Anomaly Detection with LSTM Neural Networks
• Toward Supervised Anomaly Detection
• Sum-Product Networks: A New Deep Architecture
• Deep and Confident Prediction for Time Series at Uber
• IDSGAN: Generative Adversarial Networks for Attack Generation against Intrusion Detection
• LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection
• Anomaly Detection for a Water Treatment System Using Unsupervised Machine Learning
• Mobile Big Data Analytics Using Deep Learning and Apache Spark
• Deep Structured Energy Based Models for Anomaly Detection
• Flow-based Network Traffic Generation using Generative Adversarial Networks
• DeepSign: Deep Learning for Automatic Malware Signature Generation and Classification
• Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series
• Anomaly Detection in Video Using Predictive Convolutional Long Short-Term Memory Networks
• Deep learning at the shallow end: Malware classification for non-domain experts
• Anomaly Detection using One-Class Neural Networks
• Dynamic Word Embeddings
• Multi-Sensor Prognostics using an Unsupervised Health Index based on LSTM Encoder-Decoder
• Deep Learning for Time-Series Analysis
• Deep Learning for Unsupervised Insider Threat Detection in Structured Cybersecurity Data Streams
• Deep Learning and Its Applications to Machine Health Monitoring: A Survey
• WAIC, but Why? Generative Ensembles for Robust Anomaly Detection
• Adversarial Attacks Against Medical Deep Learning Systems
• A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data
• Zero-Shot Learning -- The Good, the Bad and the Ugly
• Black-Box Attacks against RNN based Malware Detection Algorithms
• LSTM-Based System-Call Language Modeling and Robust Ensemble Method for Designing Host-Based Intrusion Detection Systems
• Comparative study of LSA vs Word2vec embeddings in small corpora: a case study in dreams database
• Detection of Anomalies in Large Scale Accounting Data using Deep Autoencoder Networks
• Multivariate Industrial Time Series with Cyber-Attack Simulation: Fault Detection Using an LSTM-based Predictive Data Model
• Automatic Rumor Detection on Microblogs: A Survey
• Learning Deep Representations of Appearance and Motion for Anomalous Event Detection
• Improving the Accuracy of Pre-trained Word Embeddings for Sentiment Analysis
• Real-Time Illegal Parking Detection System Based on Deep Learning
• RNN-based Early Cyber-Attack Detection for the Tennessee Eastman Process
• Anomaly Detection for Skin Disease Images Using Variational Autoencoder
• An investigation of a deep learning based malware detection system
• Bidirectional LSTM-CRF for Clinical Concept Extraction
• Recurrent Neural Radio Anomaly Detection
• R2-D2: ColoR-inspired Convolutional NeuRal Network (CNN)-based AndroiD Malware Detections
• Clustering and Unsupervised Anomaly Detection with L2 Normalized Deep Auto-Encoder Representations
• Novelty Detection with GAN
• Are generative deep models for novelty detection truly better?
• DOC: Deep Open Classification of Text Documents
• The model of an anomaly detector for HiLumi LHC magnets based on Recurrent Neural Networks and adaptive quantization
• Training Adversarial Discriminators for Cross-channel Abnormal Event Detection in Crowds
• Modeling Representation of Videos for Anomaly Detection using Deep Learning: A Review
• MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks
• Image denoising and restoration with CNN-LSTM Encoder Decoder with Direct Attention
• VOS: a Method for Variational Oversampling of Imbalanced Data
• One-Class Adversarial Nets for Fraud Detection
• Adversary Resistant Deep Neural Networks with an Application to Malware Detection
• Solving the "false positives" problem in fraud prediction
• MDGAN: Boosting Anomaly Detection Using \\Multi-Discriminator Generative Adversarial Networks
• Estimation of Dimensions Contributing to Detected Anomalies with Variational Autoencoders
• Recurrent Neural Networks for anomaly detection in the Post-Mortem time series of LHC superconducting magnets
• Detecting Anomalous Faces with 'No Peeking' Autoencoders
• Attentioned Convolutional LSTM InpaintingNetwork for Anomaly Detection in Videos
• Generalized Zero-Shot Learning for Action Recognition with Web-Scale Video Data
• Deep Convolutional Neural Networks for Anomaly Event Classification on Distributed Systems
• Group Anomaly Detection using Deep Generative Models
• When deep learning meets security

Cited by in corpus (167)

• A Comprehensive Survey on Graph Anomaly Detection with Deep Learning
• Deep Learning for Time Series Anomaly Detection: A Survey
• A Survey on Anomaly Detection for Technical Systems using LSTM Networks
• Generalized Out-of-Distribution Detection: A Survey
• IoT Anomaly Detection Methods and Applications: A Survey
• MST-GAT: A Multimodal Spatial-Temporal Graph Attention Network for Time Series Anomaly Detection
• An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Series
• Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey
• A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions
• Deep Learning for Anomaly Detection in Log Data: A Survey
• Real-World Anomaly Detection by using Digital Twin Systems and Weakly-Supervised Learning
• Anomaly Detection in Medical Imaging with Deep Perceptual Autoencoders
• adVAE: A self-adversarial variational autoencoder with Gaussian anomaly prior knowledge for anomaly detection
• Unsupervised phase discovery with deep anomaly detection
• DTAAD: Dual Tcn-Attention Networks for Anomaly Detection in Multivariate Time Series Data
• Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detection
• Time Series Anomaly Detection for Cyber-Physical Systems via Neural System Identification and Bayesian Filtering
• One-Class Classification: A Survey
• Self-Supervised Anomaly Detection in Computer Vision and Beyond: A Survey and Outlook
• Testing for Outliers with Conformal p-values
• MOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detection
• Utilizing XAI technique to improve autoencoder based model for computer network anomaly detection with shapley additive explanation(SHAP)
• NF-GNN: Network Flow Graph Neural Networks for Malware Detection and Classification
• The GIGANTES dataset: precision cosmology from voids in the machine learning era
• Unsupervised Anomaly Detection in Stream Data with Online Evolving Spiking Neural Networks
• DASVDD: Deep Autoencoding Support Vector Data Descriptor for Anomaly Detection
• Semi-supervised detection of structural damage using Variational Autoencoder and a One-Class Support Vector Machine
• Deep Learning-Based Anomaly Detection in Cyber-Physical Systems: Progress and Opportunities
• Deep Learning Methods for Credit Card Fraud Detection
• Target specific mining of COVID-19 scholarly articles using one-class approach
• A Deep Learning Approach for Active Anomaly Detection of Extragalactic Transients
• Learning Memory-guided Normality for Anomaly Detection
• Attribute Restoration Framework for Anomaly Detection
• Online Model-based Anomaly Detection in Multivariate Time Series: Taxonomy, Survey, Research Challenges and Future Directions
• Lifelong Continual Learning for Anomaly Detection: New Challenges, Perspectives, and Insights
• Unsupervised Outlier Detection using Memory and Contrastive Learning
• VELC: A New Variational AutoEncoder Based Model for Time Series Anomaly Detection
• A new interpretable unsupervised anomaly detection method based on residual explanation
• Meta-survey on outlier and anomaly detection
• Graph Mining for Cybersecurity: A Survey
• Motion and Region Aware Adversarial Learning for Fall Detection with Thermal Imaging
• Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Training
• Deep Semi-Supervised Anomaly Detection
• A new measure between sets of probability distributions with applications to erratic financial behavior
• Perceptual Image Anomaly Detection
• Unsupervised learning of anomalous diffusion data
• Variational quantum one-class classifier
• Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals
• Role of Data Augmentation Strategies in Knowledge Distillation for Wearable Sensor Data
• Autoencoder-based Anomaly Detection in Streaming Data with Incremental Learning and Concept Drift Adaptation
• Image/Video Deep Anomaly Detection: A Survey
• MAD: Self-Supervised Masked Anomaly Detection Task for Multivariate Time Series
• A Transfer Learning Framework for Anomaly Detection Using Model of Normality
• A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges
• Neural network-based anomaly detection for high-resolution X-ray spectroscopy
• Reinforcement Learning for Photonic Component Design
• Unsupervised Multivariate Time-Series Transformers for Seizure Identification on EEG
• Towards Visually Explaining Variational Autoencoders
• Deep Learning for Insider Threat Detection: Review, Challenges and Opportunities
• Detection of Accounting Anomalies in the Latent Space using Adversarial Autoencoder Neural Networks
• Acoustic Leak Detection in Water Networks
• Deep learning models for predictive maintenance: a survey, comparison, challenges and prospect
• ALGAN: Anomaly Detection by Generating Pseudo Anomalous Data via Latent Variables
• Adjusting for Autocorrelated Errors in Neural Networks for Time Series
• Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Images
• Recomposition vs. Prediction: A Novel Anomaly Detection for Discrete Events Based On Autoencoder
• PyLightcurve-torch: a transit modelling package for deep learning applications in PyTorch
• Foundation Models and Transformers for Anomaly Detection: A Survey
• Normality-Calibrated Autoencoder for Unsupervised Anomaly Detection on Data Contamination
• Puzzle-AE: Novelty Detection in Images through Solving Puzzles
• Exathlon: A Benchmark for Explainable Anomaly Detection over Time Series
• Multi-Modal Anomaly Detection for Unstructured and Uncertain Environments
• Novelty Detection Via Blurring
• The Hidden Uncertainty in a Neural Networks Activations
• Addressing Artificial Intelligence Bias in Retinal Disease Diagnostics
• A Deep Learning based Detection Method for Combined Integrity-Availability Cyber Attacks in Power System
• How to find a unicorn: a novel model-free, unsupervised anomaly detection method for time series
• Quantum support vector data description for anomaly detection
• Stateful Detection of Model Extraction Attacks
• Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders
• Identification of Rare Cortical Folding Patterns using Unsupervised Deep Learning
• Anomaly Detection for Multivariate Time Series on Large-scale Fluid Handling Plant Using Two-stage Autoencoder
• Anomalous Example Detection in Deep Learning: A Survey
• SafeAMC: Adversarial training for robust modulation recognition models
• Cluster Purging: Efficient Outlier Detection based on Rate-Distortion Theory
• On the Resilience of Machine Learning-Based IDS for Automotive Networks
• Unsupervised Incremental Learning with Dual Concept Drift Detection for Identifying Anomalous Sequences
• Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples
• PETGEN: Personalized Text Generation Attack on Deep Sequence Embedding-based Classification Models
• Memory-augmented Adversarial Autoencoders for Multivariate Time-series Anomaly Detection with Deep Reconstruction and Prediction
• Regional-Local Adversarially Learned One-Class Classifier Anomalous Sound Detection in Global Long-Term Space
• PAC-Wrap: Semi-Supervised PAC Anomaly Detection
• H-VGRAE: A Hierarchical Stochastic Spatial-Temporal Embedding Method for Robust Anomaly Detection in Dynamic Networks
• Understanding the Effect of Bias in Deep Anomaly Detection
• Abnormal Event Detection in Urban Surveillance Videos Using GAN and Transfer Learning
• Quantized Non-Volatile Nanomagnetic Synapse based Autoencoder for Efficient Unsupervised Network Anomaly Detection
• Semi-supervised Anomaly Detection on Attributed Graphs
• SLA${}^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation
• SincVAE: A new semi-supervised approach to improve anomaly detection on EEG data using SincNet and variational autoencoder
• A Simple Framework for Uncertainty in Contrastive Learning
• Triggering Dark Showers with Conditional Dual Auto-Encoders
• Quick survey of graph-based fraud detection methods
• Deep Variational Semi-Supervised Novelty Detection
• Constructing a meta-learner for unsupervised anomaly detection
• mmFall: Fall Detection using 4D MmWave Radar and a Hybrid Variational RNN AutoEncoder
• Self-Supervised Representation Learning for Visual Anomaly Detection
• Extending Isolation Forest for Anomaly Detection in Big Data via K-Means
• Deep Random Projection Outlyingness for Unsupervised Anomaly Detection
• Automatic Validation of Textual Attribute Values in E-commerce Catalog by Learning with Limited Labeled Data
• CloudFindr: A Deep Learning Cloud Artifact Masker for Satellite DEM Data
• A Thousand Words are Worth More Than One Recording: NLP Based Speaker Change Point Detection
• Visual Analytics of Anomalous User Behaviors: A Survey
• Novelty Detection via Robust Variational Autoencoding
• An Algorithm for Out-Of-Distribution Attack to Neural Network Encoder
• Learning Retrospective Knowledge with Reverse Reinforcement Learning
• Learning Global and Local Features of Normal Brain Anatomy for Unsupervised Abnormality Detection
• Image-based Plant Disease Diagnosis with Unsupervised Anomaly Detection Based on Reconstructability of Colors
• A Robust Classification-autoencoder to Defend Outliers and Adversaries
• Importance Weighted Adversarial Discriminative Transfer for Anomaly Detection
• Enhancing Unsupervised Anomaly Detection with Score-Guided Network
• New Methods and Datasets for Group Anomaly Detection From Fundamental Physics
• Real-time detection of uncalibrated sensors using Neural Networks
• Online Safety Assurance for Deep Reinforcement Learning
• Anomaly Detection by Recombining Gated Unsupervised Experts
• AnoNet: Weakly Supervised Anomaly Detection in Textured Surfaces
• A Survey on Assessing the Generalization Envelope of Deep Neural Networks: Predictive Uncertainty, Out-of-distribution and Adversarial Samples
• Novelty Detection in Sequential Data by Informed Clustering and Modeling
• Probabilistic Outlier Detection and Generation
• A Survey on Proactive Customer Care: Enabling Science and Steps to Realize it
• Nonparametric Density Estimation from Markov Chains
• Anomaly Detection Based on Selection and Weighting in Latent Space
• Isconna: Streaming Anomaly Detection with Frequency and Patterns
• Meta-Learning for One-Class Classification with Few Examples using Order-Equivariant Network
• Adversarial Robustness for Machine Learning Cyber Defenses Using Log Data
• A Heuristic Quantum-Classical Algorithm for Modeling Substitutionally Disordered Binary Crystalline Materials
• Evaluation of an Anomaly Detector for Routers using Parameterizable Malware in an IoT Ecosystem
• OrionBench: Benchmarking Time Series Generative Models in the Service of the End-User
• Can't Boil This Frog: Robustness of Online-Trained Autoencoder-Based Anomaly Detectors to Adversarial Poisoning Attacks
• Constrained Deep One-Class Feature Learning For Classifying Imbalanced Medical Images
• Anomaly Rule Detection in Sequence Data
• Towards Fair Deep Anomaly Detection
• Deep Residual Flow for Out of Distribution Detection
• Data-Driven Construction of Data Center Graph of Things for Anomaly Detection
• Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection
• Anomaly Detection in Smart Manufacturing with an Application Focus on Robotic Finishing Systems: A Review
• Deep convolutional autoencoder for cryptocurrency market analysis
• Anomaly-Injected Deep Support Vector Data Description for Text Outlier Detection
• Dividing Deep Learning Model for Continuous Anomaly Detection of Inconsistent ICT Systems
• What classifiers know what they don't?
• Reconstruct Anomaly to Normal: Adversarial Learned and Latent Vector-constrained Autoencoder for Time-series Anomaly Detection
• Detecting Anomalies Through Contrast in Heterogeneous Data
• A multi-task learning-based optimization approach for finding diverse sets of material microstructures with desired properties and its application to texture optimization
• A Promotion Method for Generation Error Based Video Anomaly Detection
• OLED: One-Class Learned Encoder-Decoder Network with Adversarial Context Masking for Novelty Detection
• Investigation Into the Viability of Neural Networks as a Means for Anomaly Detection in Experiments Like Atlas at the LHC
• Testing for Typicality with Respect to an Ensemble of Learned Distributions
• IPOF: An Extremely and Excitingly Simple Outlier Detection Booster via Infinite Propagation
• Kullback-Leibler Divergence-Based Out-of-Distribution Detection with Flow-Based Generative Models
• Self-Organizing Map assisted Deep Autoencoding Gaussian Mixture Model for Intrusion Detection
• Dual-encoder Bidirectional Generative Adversarial Networks for Anomaly Detection
• Deep Unsupervised Image Anomaly Detection: An Information Theoretic Framework
• Time-Window Group-Correlation Support vs. Individual Features: A Detection of Abnormal Users
• Y-GAN: Learning Dual Data Representations for Efficient Anomaly Detection
• Outlier Detection Using a Novel method: Quantum Clustering
• Online Anomaly Detection with Sparse Gaussian Processes
• Sub-clusters of Normal Data for Anomaly Detection
• Batch Uniformization for Minimizing Maximum Anomaly Score of DNN-based Anomaly Detection in Sounds