Likelihood-based generative models are a promising resource to detect out-of-distribution
(OOD) inputs which could compromise the robustness or reliability of a machine learning …

Abstract Out-of-distribution (OOD) detection is essential to prevent anomalous inputs from
causing a model to fail during deployment. While improved OOD detection methods have …

Recent work has shown that deep generative models can assign higher likelihood to out-of-
distribution data sets than to their training data (Nalisnick et al., 2019; Choi et al., 2019). We …

Anomaly detection systems can accurately identify malicious network traffic, providing
network security. With the development of internet technology, network attacks are becoming …

The recent, counter-intuitive discovery that deep generative models (DGMs) can frequently
assign a higher likelihood to outliers has implications for both outlier detection applications …

Recent work has shown that Neural Ordinary Differential Equations (ODEs) can serve as
generative models of images using the perspective of Continuous Normalizing Flows …

Recent research has revealed that deep generative models including flow-based models
and Variational Autoencoders may assign higher likelihoods to out-of-distribution (OOD) …

In this paper, we propose a compression-based anomaly detection method for time series
and sequence data using a pattern dictionary. The proposed method is capable of learning …

Anomaly detection refers to the problem of identifying abnormal behaviour within a set of
measurements. In many cases, one has some statistical model for normal data, and wishes …

Anomaly detection is important in many research areas including fraud detection and
biological change detection. However, anomaly detection is a difficult task due to the lack of …