Toward Supervised Anomaly Detection

Abstract

Anomaly detection is being regarded as an unsupervised learning task as anomalies stem from adversarial or unlikely events with unknown distributions. However, the predictive performance of purely unsupervised anomaly detection often fails to match the required detection rates in many tasks and there exists a need for labeled data to guide the model generation. Our first contribution shows that classical semi-supervised approaches, originating from a supervised classifier, are inappropriate and hardly detect new and unknown anomalies. We argue that semi-supervised anomaly detection needs to ground on the unsupervised learning paradigm and devise a novel algorithm that meets this requirement. Although being intrinsically non-convex, we further show that the optimization problem has a convex equivalent under relatively mild assumptions. Additionally, we propose an active learning strategy to automatically filter candidates for labeling. In an empirical study on network intrusion detection data, we observe that the proposed learning methodology requires much less labeled data than the state-of-the-art, while achieving higher detection accuracies.

Cited by in corpus (50)

• Deep Learning for Anomaly Detection: A Survey
• A Unifying Review of Deep and Shallow Anomaly Detection
• Unsupervised and Semi-supervised Anomaly Detection with LSTM Neural Networks
• Generalized Out-of-Distribution Detection: A Survey
• A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions
• Unsupervised Detection of Anomalous Sound based on Deep Learning and the Neyman-Pearson Lemma
• A Survey on Unsupervised Anomaly Detection Algorithms for Industrial Images
• Towards Explaining Anomalies: A Deep Taylor Decomposition of One-Class Models
• A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data
• Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Data
• Real-Time Anomaly Detection for Streaming Analytics
• SSD: A Unified Framework for Self-Supervised Outlier Detection
• Explainable Deep Few-shot Anomaly Detection with Deviation Networks
• Living-Off-The-Land Command Detection Using Active Learning
• Deep Weakly-supervised Anomaly Detection
• Deep Semi-Supervised Anomaly Detection
• Consistency-guided semi-supervised outlier detection in heterogeneous data using fuzzy rough sets
• Active anomaly detection based on deep one-class classification
• RLAD: Time Series Anomaly Detection through Reinforcement Learning and Active Learning
• Learning Representations for Outlier Detection on a Budget
• Anomaly Detection with Score Distribution Discrimination
• The Clever Hans Effect in Anomaly Detection
• NFAD: Fixing anomaly detection using normalizing flows
• Anomaly Detection in Images
• Effectiveness of Tree-based Ensembles for Anomaly Discovery: Insights, Batch and Streaming Active Learning
• Normality-Calibrated Autoencoder for Unsupervised Anomaly Detection on Data Contamination
• Rethinking Assumptions in Deep Anomaly Detection
• Wisdom of the Contexts: Active Ensemble Learning for Contextual Anomaly Detection
• Active Anomaly Detection via Ensembles
• Supervised Anomaly Detection based on Deep Autoregressive Density Estimators
• Cluster Purging: Efficient Outlier Detection based on Rate-Distortion Theory
• ESAD: End-to-end Deep Semi-supervised Anomaly Detection
• Meta-AAD: Active Anomaly Detection with Deep Reinforcement Learning
• Arrays of (locality-sensitive) Count Estimators (ACE): High-Speed Anomaly Detection via Cache Lookups
• Little Help Makes a Big Difference: Leveraging Active Learning to Improve Unsupervised Time Series Anomaly Detection
• Fast Cross-Validation for Incremental Learning
• Interpretable Transformation and Analysis of Timelines through Learning via Surprisability
• Integrated Clustering and Anomaly Detection (INCAD) for Streaming Data (Revised)
• Deep Variational Semi-Supervised Novelty Detection
• LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection
• Label-Informed Outlier Detection Based on Granule Density
• Latent Laplacian Maximum Entropy Discrimination for Detection of High-Utility Anomalies
• Online Anomaly Detection via Class-Imbalance Learning
• Framework for Multi-task Multiple Kernel Learning and Applications in Genome Analysis
• GLAD: GLocalized Anomaly Detection via Human-in-the-Loop Learning
• Towards Fair Deep Anomaly Detection
• Unsupervised Detection and Explanation of Latent-class Contextual Anomalies
• Time Series Anomaly Detection with label-free Model Selection
• Multi-Class Anomaly Detection
• IPOF: An Extremely and Excitingly Simple Outlier Detection Booster via Infinite Propagation