Robust Anomaly Detection using Reconstructive Adversarial Network

Detecting abnormal service performance is significant for Internet-based service management and operation. Recent advances in anomaly detection methods prefer unsupervised learning algorithms since they can work without manually labeled data. However, existing unsupervised methods converge into suboptimal solutions due to their heuristic-based objectives. Moreover, they frequently rely on the strong assumption that noise follows a Gaussian distribution, and their detection accuracy is also highly sensitive to threshold settings. To detect anomalies precisely and robustly, we present Adran, an unsupervised anomaly detection model that introduces adversarial learning into a reconstructive model, generating a reconstructive adversarial network with an anomaly detection-based training objective. It tolerates non-Gaussian noise by activating the discriminator with a non-smooth function. Our experimental results demonstrate that Adran achieves an improvement of ≥32% over the state-of-the-art methods in terms of F-score. Moreover, the robustness analysis demonstrates that it is reasonably easy and straightforward to set an appropriate threshold using Adran.