Anomaly Detection using One-Class Neural Networks

2018/02/18 by Raghavendra Chalapathy, Aditya Krishna Menon, Chalapathy, Raghavendra +3 · 13 citations
Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Network Security and Intrusion Detection #Neural and Evolutionary Computing (cs.NE)

paper · pdf · doi:10.48550/arxiv.1802.06360

openalex publication_date 2018/02/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose a one-class neural network (OC-NN) model to detect anomalies in complex data sets. OC-NN combines the ability of deep networks to extract a progressively rich representation of data with the one-class objective of creating a tight envelope around normal data. The OC-NN approach breaks new ground for the following crucial reason: data representation in the hidden layer is driven by the OC-NN objective and is thus customized for anomaly detection. This is a departure from other approaches which use a hybrid approach of learning deep features using an autoencoder and then feeding the features into a separate anomaly detection method like one-class SVM (OC-SVM). The hybrid OC-SVM approach is sub-optimal because it is unable to influence representational learning in the hidden layers. A comprehensive set of experiments demonstrate that on complex data sets (like CIFAR and GTSRB), OC-NN performs on par with state-of-the-art methods and outperformed conventional shallow methods in some scenarios.

Citations

• On Estimation of a Probability Density Function and Mode
• Estimating the Support of a High-Dimensional Distribution
• A Survey on Transfer Learning
• Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
• Learning Multiple Layers of Features from Tiny Images

Cited by

• Unsupervised Anomaly Detection with an Enhanced Teacher for Student-Teacher Feature Pyramid Matching
• Sparse, self-organizing ensembles of local kernels detect rare statistical anomalies
• Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection
• StructuralDecompose: A Modular Framework for Robust Time Series Decomposition in R
• Representation-Based Data Quality Audits for Audio
• INQMAD: incremental streaming anomaly detection with density matrices, quantum measurement, and density estimation
• Deep Learning for Anomaly Detection: A Survey
• Who is in Control? Practical Physical Layer Attack and Defense for mmWave based Sensing in Autonomous Vehicles
• Explainable Deep One-Class Classification
• DDR-ID: Dual Deep Reconstruction Networks Based Image Decomposition for Anomaly Detection
• Deep Semi-Supervised Anomaly Detection
• ℓ_p-Norm Multiple Kernel One-Class Fisher Null-Space
• Student-Teacher Feature Pyramid Matching for Anomaly Detection

Related

• Deep Anomaly Detection with Deviation Networks
• Learning to Detect Multi-class Anomalies with Just One Normal Image Prompt
• Exploring the Optimization Objective of One-Class Classification for Anomaly Detection
• A Unifying Review of Deep and Shallow Anomaly Detection
• Unsupervised Surrogate Anomaly Detection