Efficient GAN-Based Anomaly Detection

Abstract

Generative adversarial networks (GANs) are able to model the complex highdimensional distributions of real-world data, which suggests they could be effective for anomaly detection. However, few works have explored the use of GANs for the anomaly detection task. We leverage recently developed GAN models for anomaly detection, and achieve state-of-the-art performance on image and network intrusion datasets, while being several hundred-fold faster at test time than the only published GAN-based method.

arXiv commentUpdated version of this work is published at ICDM 2018, see arXiv:1812.02288 . Submitted to the ICLR Workshop 2018

References in corpus (1)

• Generative Adversarial Networks: An Overview

Cited by in corpus (79)

• Deep Learning for Anomaly Detection: A Survey
• Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders
• A Survey on Anomaly Detection for Technical Systems using LSTM Networks
• Accelerating Materials Development via Automation, Machine Learning, and High-Performance Computing
• Anomaly Detection with Generative Adversarial Networks for Multivariate Time Series
• MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks
• MOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detection
• Maximum Entropy Generators for Energy-Based Models
• Generative Adversarial Active Learning for Unsupervised Outlier Detection
• DASVDD: Deep Autoencoding Support Vector Data Descriptor for Anomaly Detection
• Machine Learning in NextG Networks via Generative Adversarial Networks
• Low-Quality Training Data Only? A Robust Framework for Detecting Encrypted Malicious Network Traffic
• Deep Learning-Based Anomaly Detection in Cyber-Physical Systems: Progress and Opportunities
• DermGAN: Synthetic Generation of Clinical Skin Images with Pathology
• Attribute Restoration Framework for Anomaly Detection
• AnoSeg: Anomaly Segmentation Network Using Self-Supervised Learning
• Federated PCA on Grassmann Manifold for IoT Anomaly Detection
• Masked Transformer for image Anomaly Localization
• Chester: A Web Delivered Locally Computed Chest X-Ray Disease Prediction System
• Small-GAN: Speeding Up GAN Training Using Core-sets
• Perceptual Image Anomaly Detection
• Robust Subspace Recovery Layer for Unsupervised Anomaly Detection
• A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges
• Internet Congestion Control via Deep Reinforcement Learning
• Anomaly Detection with Score Distribution Discrimination
• Anomaly Detection with Tensor Networks
• Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detection
• ALGAN: Anomaly Detection by Generating Pseudo Anomalous Data via Latent Variables
• Efficient GAN-based method for cyber-intrusion detection
• Visual Anomaly Detection for Images: A Survey
• Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples
• Anomaly Detection in Images
• Exathlon: A Benchmark for Explainable Anomaly Detection over Time Series
• Rethinking Assumptions in Deep Anomaly Detection
• Novelty Detection Via Blurring
• Tail of Distribution GAN (TailGAN): Generative-Adversarial-Network-Based Boundary Formation
• Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary
• Brain Tumor Anomaly Detection via Latent Regularized Adversarial Network
• RSM-GAN: A Convolutional Recurrent GAN for Anomaly Detection in Contaminated Seasonal Multivariate Time Series
• Fence GAN: Towards Better Anomaly Detection
• SAFE-OCC: A Novelty Detection Framework for Convolutional Neural Network Sensors and its Application in Process Control
• Novelty Detection via Non-Adversarial Generative Network
• When to Intervene: Detecting Abnormal Mood using Everyday Smartphone Conversations
• on the effectiveness of generative adversarial network on anomaly detection
• Regional-Local Adversarially Learned One-Class Classifier Anomalous Sound Detection in Global Long-Term Space
• Out-of-Distribution Detection Using Neural Rendering Generative Models
• IoT Threat Detection Testbed Using Generative Adversarial Networks
• Clustering with Outlier Removal
• Coupled IGMM-GANs for deep multimodal anomaly detection in human mobility data
• Discriminative-Generative Representation Learning for One-Class Anomaly Detection
• Interpretable Transformation and Analysis of Timelines through Learning via Surprisability
• SLA${}^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation
• Learning Latent Space Energy-Based Prior Model
• RCC-Dual-GAN: An Efficient Approach for Outlier Detection with Few Identified Anomalies
• Joint Training of Variational Auto-Encoder and Latent Energy-Based Model
• LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection
• Image-based Plant Disease Diagnosis with Unsupervised Anomaly Detection Based on Reconstructability of Colors
• Unsupervised Region-based Anomaly Detection in Brain MRI with Adversarial Image Inpainting
• Detecting Abnormal Operations in Concentrated Solar Power Plants from Irregular Sequences of Thermal Images
• PNUNet: Anomaly Detection using Positive-and-Negative Noise based on Self-Training Procedure
• OIAD: One-for-all Image Anomaly Detection with Disentanglement Learning
• Attention Map-guided Two-stage Anomaly Detection using Hard Augmentation
• FaultNet: Faulty Rail-Valves Detection using Deep Learning and Computer Vision
• Acoustic anomaly detection via latent regularized gaussian mixture generative adversarial networks
• Quantitatively rating galaxy simulations against real observations with anomaly detection
• Probabilistic Outlier Detection and Generation
• Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection
• OMASGAN: Out-of-Distribution Minimum Anomaly Score GAN for Sample Generation on the Boundary
• Towards Fair Deep Anomaly Detection
• New Perspective on Progressive GANs Distillation for One-class Novelty Detection
• Finding the optimal Nash equilibrium in a discrete Rosenthal congestion game using the Quantum Alternating Operator Ansatz
• STEP-GAN: A Step-by-Step Training for Multi Generator GANs with application to Cyber Security in Power Systems
• Deep Clustering based Fair Outlier Detection
• Distributed Anomaly Detection in Edge Streams using Frequency based Sketch Datastructures
• Sub-clusters of Normal Data for Anomaly Detection
• Dual-encoder Bidirectional Generative Adversarial Networks for Anomaly Detection
• Semi-Supervised Surface Anomaly Detection of Composite Wind Turbine Blades From Drone Imagery
• IPOF: An Extremely and Excitingly Simple Outlier Detection Booster via Infinite Propagation
• Transfer Learning from an Auxiliary Discriminative Task for Unsupervised Anomaly Detection