adVAE: A self-adversarial variational autoencoder with Gaussian anomaly prior knowledge for anomaly detection

Abstract

Recently, deep generative models have become increasingly popular in unsupervised anomaly detection. However, deep generative models aim at recovering the data distribution rather than detecting anomalies. Besides, deep generative models have the risk of overfitting training samples, which has disastrous effects on anomaly detection performance. To solve the above two problems, we propose a Self-adversarial Variational Autoencoder with a Gaussian anomaly prior assumption. We assume that both the anomalous and the normal prior distribution are Gaussian and have overlaps in the latent space. Therefore, a Gaussian transformer net T is trained to synthesize anomalous but near-normal latent variables. Keeping the original training objective of Variational Autoencoder, besides, the generator G tries to distinguish between the normal latent variables and the anomalous ones synthesized by T, and the encoder E is trained to discriminate whether the output of G is real. These new objectives we added not only give both G and E the ability to discriminate but also introduce additional regularization to prevent overfitting. Compared with the SOTA baselines, the proposed model achieves significant improvements in extensive experiments. Datasets and our model are available at a Github repository.

arXiv commentThis paper has been accepted by Knowledge-based Systems

References in corpus (7)

• Auto-Encoding Variational Bayes
• Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning
• Deep Learning for Anomaly Detection: A Survey
• InfoVAE: Information Maximizing Variational Autoencoders
• IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis
• Sequential Neural Models with Stochastic Layers
• Less is More: Building Selective Anomaly Ensembles

Cited by in corpus (9)

• One-Class Graph Neural Networks for Anomaly Detection in Attributed Networks
• MOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detection
• Anomaly Detection in Aerial Videos with Transformers
• Attribute Restoration Framework for Anomaly Detection
• Recomposition vs. Prediction: A Novel Anomaly Detection for Discrete Events Based On Autoencoder
• GAN-AE : An anomaly detection algorithm for New Physics search in LHC data
• Quadratic Neuron-empowered Heterogeneous Autoencoder for Unsupervised Anomaly Detection
• Gaussian Process Based Message Filtering for Robust Multi-Agent Cooperation in the Presence of Adversarial Communication
• Time-Window Group-Correlation Support vs. Individual Features: A Detection of Abnormal Users