Deep Learning for Anomaly Detection

Abstract

Anomaly detection, a.k.a. outlier detection, has been a lasting yet active research area in various research communities for several decades. There are still some unique problem complexities and challenges that require advanced approaches. In recent years, deep learning enabled anomaly detection, i.e., deep anomaly detection, has emerged as a critical direction. This paper reviews the research of deep anomaly detection with a comprehensive taxonomy of detection methods, covering advancements in three high-level categories and 11 fine-grained categories of the methods. We review their key intuitions, objective functions, underlying assumptions, advantages and disadvantages, and discuss how they address the aforementioned challenges. We further discuss a set of possible future opportunities and new perspectives on addressing the challenges. CCS Concepts: • Computing methodologies → Anomaly detection; Neural networks.

Modified Autoencoder Training and Scoring for Robust Unsupervised Anomaly Detection in Deep Learning

“…In order to provide a fair evaluation, some holdout sets are used for choosing reasonable hyperparameters for each architecture and domain. This use of labeled data may be considered a form of weakly supervised learning; however, the use is only intended to provide a reasonable comparison and is not required in practice [38]. Details on hyperparameter tuning are provided in each of the following subsections.…”

Medical Fraud and Abuse Detection System Based on Machine Learning

“…However, a supervised learning algorithm depends heavily on datasets [ 8 ]. As the healthcare scenario is complicated, a dataset is usually not comprehensive, which often causes the result to be seriously over-fitted in real-world scenarios.…”

GAN based Augmentation for Improving Anomaly Detection Accuracy in Host-based Intrusion Detection Systems

“…Also it discussed the computational complexity of anomaly detection techniques. The study [25] discussed the deep model based anomaly detection techniques used to overcome the limitations from traditional algorithms in real world examples from LinkedIn production systems. This paper [26] described a computationally efficient anomaly based intrusion detection model through the incorporation of stacked CNNs with GRUs to obtain reduced training times.…”

“…As mentioned in the paper [25], recent advancement in deep learning techniques has made it possible to largely improve anomaly detection performance compared to the classical approaches. Therefore, our work has performed CNN-based classification for anomaly detection and GAN-based augmentation for oversampling of minority classes.…”