Divergence-driven generative adversarial networks for semi-supervised anomaly detection

García Fernández, ManuelSalmerón Silvera, José Luis2026-05-302026-05-302026Garcia-Fernandez, M., & Salmeron, J. L. (2026). Divergence-driven generative adversarial networks for semi-supervised anomaly detection. Neurocomputing, 690, 133834. https://doi.org/10.1016/j.neucom.2026.1338340925-23121872-8286https://hdl.handle.net/11268/17127Anomaly detection is a critical challenge due to the extreme class imbalance between anomalous and normal data instances. This study presents a semi-supervised anomaly detection framework based on GANs, in which the discriminator is repurposed as a direct classifier for anomaly detection. This research advances the application of GANs in anomaly detection by introducing a divergence-driven training paradigm and validating its effectiveness through extensive experimentation with credit card fraud data and Twitter bot accounts.engComputación y tecnologíaDivergence-driven generative adversarial networks for semi-supervised anomaly detectionjournal article10.1016/j.neucom.2026.133834embargoed accessMatemáticasInformáticaInteligencia artificialGoal 8: Promote inclusive and sustainable economic growth, employment and decent work for allGoal 9: Build resilient infrastructure, promote sustainable industrialization and foster innovation