Adversarial Anomaly Detection using Gaussian Priors and Nonlinear Anomaly Scores

Lüer, Fiete; Weber, Tobias ; Dolgich, Maxim und Böhm, Christian (2023): Adversarial Anomaly Detection using Gaussian Priors and Nonlinear Anomaly Scores. 23rd IEEE International Conference on Data Mining (IEEE ICDM), Shanghai, China, 01.-04. Dezember 2023. Wang, Jihe; He, Yi; Dinh, Thang N.; Grant, Christan; Qiu, Meikang und Pedrycz, Witold (eds.) : In: 23rd IEEE International Conference on Data Mining Workshops, Piscataway, NJ: IEEE. pp. 550-559

Abstract

Anomaly detection in imbalanced datasets is a frequent and crucial problem, especially in the medical domain where retrieving and labeling irregularities is often expensive. By combining the generative stability of a β-variational autoencoder (VAE) with the discriminative strengths of generative adversarial networks (GANs), we propose a novel model, β-VAEGAN. We investigate methods for composing anomaly scores based on the discriminative and reconstructive capabilities of our model. Existing work focuses on linear combinations of these components to determine if data is anomalous. We advance existing work by training a kernelized support vector machine (SVM) on the respective error components to also consider nonlinear relationships. This improves anomaly detection performance, while allowing faster optimization. Lastly, we use the deviations from the Gaussian prior of β-VAEGAN to form a novel anomaly score component. In comparison to state-of-the-art work, we improve the F 1 score during anomaly detection from 0.85 to 0.92 on the widely used MITBIH Arrhythmia Database.

• Item Type: Conference or Workshop Item (Paper)
• Faculties: Mathematics, Computer Science and Statistics > Statistics > Chairs/Working Groups > Computational Statistics; Mathematics, Computer Science and Statistics > Computer Science
• Subjects: 000 Computer science, information and general works > 004 Data processing computer science; 500 Science > 510 Mathematics; 600 Technology > 610 Medicine and health
• ISBN: 979-8-3503-8164-1 ; 979-8-3503-8165-8
• Place of Publication: Piscataway, NJ
• Language: English