R2-AD2: Detecting Anomalies by Analysing the Raw Gradient

06/21/2022
by   Jan-Philipp Schulze, et al.
14

Neural networks follow a gradient-based learning scheme, adapting their mapping parameters by back-propagating the output loss. Samples unlike the ones seen during training cause a different gradient distribution. Based on this intuition, we design a novel semi-supervised anomaly detection method called R2-AD2. By analysing the temporal distribution of the gradient over multiple training steps, we reliably detect point anomalies in strict semi-supervised settings. Instead of domain dependent features, we input the raw gradient caused by the sample under test to an end-to-end recurrent neural network architecture. R2-AD2 works in a purely data-driven way, thus is readily applicable in a variety of important use cases of anomaly detection.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/29/2021

Elsa: Energy-based learning for semi-supervised anomaly detection

Anomaly detection aims at identifying deviant instances from the normal ...
research
02/19/2021

Self-Taught Semi-Supervised Anomaly Detection on Upper Limb X-rays

Detecting anomalies in musculoskeletal radiographs is of paramount impor...
research
05/23/2023

SAD: Semi-Supervised Anomaly Detection on Dynamic Graphs

Anomaly detection aims to distinguish abnormal instances that deviate si...
research
05/17/2019

Online Multivariate Anomaly Detection and Localization for High-dimensional Settings

This paper considers the real-time detection of anomalies in high-dimens...
research
04/11/2018

Bayesian Semi-Supervised Tensor Decomposition using Natural Gradients for Anomaly Detection

Anomaly Detection has several important applications. In this paper, our...
research
05/07/2021

Energy-Based Anomaly Detection and Localization

This brief sketches initial progress towards a unified energy-based solu...
research
01/23/2020

Universal Data Anomaly Detection via Inverse Generative Adversary Network

The problem of detecting data anomaly is considered. Under the null hypo...

Please sign up or login with your details

Forgot password? Click here to reset