Robust anomaly detection via adversarial counterfactual generation

• Published in: Knowledge and information systems 2024-12, Vol.66 (12), p.7437-7468
• Main Authors: Liguori, Angelica, Ritacco, Ettore, Pisani, Francesco Sergio, Manco, Giuseppe
• Format: Article
• Language: English
• Subjects: Anomalies; Computer Science; Data analysis; Data mining; Data Mining and Knowledge Discovery; Database Management; Information Storage and Retrieval; Information Systems and Communication Service; Information Systems Applications (incl.Internet); IT in Business; Learning; Machine learning; Reconstruction; Regular Paper; Regularization; Robustness
• ISSN: 0219-1377; 0219-3116
• DOI: 10.1007/s10115-024-02172-w

The capability to devise robust outlier and anomaly detection tools is an important research topic in machine learning and data mining. Recent techniques have been focusing on reinforcing detection with sophisticated data generation tools that successfully refine the learning process by generating variants of the data that expand the recognition capabilities of the outlier detector. In this paper, we propose ARN , a semi-supervised anomaly detection and generation method based on adversarial counterfactual reconstruction. ARN exploits a regularized autoencoder to optimize the reconstruction of variants of normal examples with minimal differences that are recognized as outliers. The combination of regularization and counterfactual reconstruction helps to stabilize the learning process, which results in both realistic outlier generation and substantially extended detection capability. In fact, the counterfactual generation enables a smart exploration of the search space by successfully relating small changes in all the actual samples from the true distribution to high anomaly scores. Experiments on several benchmark datasets show that our model improves the current state of the art by valuable margins because of its ability to model the true boundaries of the data manifold.