An Encoding Adversarial Network for Anomaly Detection

Abstract : Anomaly detection is a standard problem in Machine Learning with various applications such as health-care, predictive maintenance, and cyber-security. In such applications, the data is unbalanced: the rate of regular examples is much higher than the anomalous examples. The emergence of the Generative Adversarial Networks (GANs) have recently brought new algorithms for anomaly detection. Most of them use the generator as a proxy for the reconstruction loss. The idea is that the generator cannot reconstruct an anomaly. We develop an alternative approach for anomaly detection, based on an Encoding Adversarial Network (AnoEAN), which maps the data in a latent space (decision space), where the detection of anomalies is done directly by calculating a score. Our encoder is learned by adversarial learning, using two loss functions, the first constraining the encoder to project regular data into a Gaussian distribution and the second, to project anomalous data outside this distribution. We conduct a series of experiments on several standard bases and show that our approach outperforms the state of the art when using 10% anomalies during the learning stage and detect unseen anomalies.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02421274
Contributor : Frédéric Davesne <>
Submitted on : Friday, December 20, 2019 - 1:07:07 PM
Last modification on : Wednesday, January 8, 2020 - 1:33:54 AM

Identifiers

  • HAL Id : hal-02421274, version 1

Citation

Elies Gherbi, Blaise Hanczar, Jean-Christophe Janodet, Witold Klaudel. An Encoding Adversarial Network for Anomaly Detection. 11th Asian Conference on Machine Learning (ACML 2019), Nov 2019, Nagoya, Japan. pp.1--16. ⟨hal-02421274⟩

Share

Metrics

Record views

38