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

arXiv: https://arxiv.org/abs/1903.00904 · HTML: https://mlsanity.com/paper/1903.00904/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2019.

## Built on by (most cited first, 11 of 11)

- [Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2107.13118/) (2021)
- [Self-Supervised Masking for Unsupervised Anomaly Detection and Localization](https://mlsanity.com/paper/2205.06568/) (2022)
- [Anomaly Detection in Aerial Videos with Transformers](https://mlsanity.com/paper/2209.13363/) (2022)
- [Statistical Test for Anomaly Detections by Variational Auto-Encoders](https://mlsanity.com/paper/2402.03724/) (2024)
- [Quadratic Neuron-empowered Heterogeneous Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2204.01707/) (2022)
- [Efficient Non-Compression Auto-Encoder for Driving Noise-based Road Surface Anomaly Detection](https://mlsanity.com/paper/2111.10985/) (2021)
- [Anomaly Detection in Aeronautics Data with Quantum-compatible Discrete Deep Generative Model](https://mlsanity.com/paper/2303.12302/) (2023)
- [A Survey on Proactive Customer Care: Enabling Science and Steps to Realize it](https://mlsanity.com/paper/2110.05015/) (2021)
- [Supervised Anomaly Detection Method Combining Generative Adversarial Networks and Three-Dimensional Data in Vehicle Inspections](https://mlsanity.com/paper/2212.11507/) (2022)
- [LBL: Logarithmic Barrier Loss Function for One-class Classification](https://mlsanity.com/paper/2307.10753/) (2023)
- [Noise-Aware Misclassification Attack Detection in Collaborative DNN Inference](https://mlsanity.com/paper/2603.17914/) (2026)

## Abstract (arXiv)

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.