Deep Anomaly Detection

Deep anomaly detection aims to identify unusual data points deviating from a learned model of normality, a crucial task across diverse fields. Current research emphasizes robust methods that handle noisy or incomplete data, focusing on architectures like autoencoders, variational autoencoders, and generative adversarial networks, as well as newer approaches leveraging contrastive learning, prototype learning, and causal inference. These advancements improve the accuracy and explainability of anomaly detection, impacting applications ranging from medical image analysis and industrial process monitoring to cybersecurity and fraud detection. A significant ongoing challenge is developing methods that are both effective and robust to various data types and anomaly characteristics, while also addressing issues of fairness and security.

Papers

August 28, 2024

Efficient Slice Anomaly Detection Network for 3D Brain MRI Volume
Zeduo Zhang, Yalda Mohsenzadeh
3D Brain Deep Anomaly Detection Brain Imaging Data Network Slice

August 23, 2024

SHEDAD: SNN-Enhanced District Heating Anomaly Detection for Urban Substations
Jonne van Dreven, Abbas Cheddad, Sadi Alawadi, Ahmad Nauman Ghazi, Jad Al Koussa, Dirk Vanhoudt
Anomaly Detection Deep Anomaly Detection Anomaly Map District Heating Grid

July 29, 2024

Foundations for Unfairness in Anomaly Detection -- Case Studies in Facial Imaging Data
Michael Livanos, Ian Davidson
Anomaly Detection Case Study Label Noise Flawed Foundation Underrepresented Group Deep Anomaly Detection Spurious Feature Facial Data

May 4, 2024

Position: Quo Vadis, Unsupervised Time Series Anomaly Detection?
M. Saquib Sarfraz, Mei-Yen Chen, Lukas Layer, Kunyu Peng, Marios Koulakis
Product Specific Position Information Deep Anomaly Detection Unsupervised Time Series Anomaly Detection Novel Deep Learning Model

February 15, 2024

Backdoor Attack against One-Class Sequential Anomaly Detection Models
He Cheng, Shuhan Yuan
Anomaly Detection Backdoor Attack Deep Anomaly Detection

February 6, 2024

IoT Network Traffic Analysis with Deep Learning
Mei Liu, Leon Yang
Deep Learning Machine Learning Internet of Thing Deep Learning Algorithm Internet of Thing Network Deep Anomaly Detection IoT Traffic

December 14, 2023

Deep Anomaly Detection in Text
Andrei Manolache
Anomaly Detection Self Supervised Learning Text Modality Unsupervised Anomaly Detection Deep Anomaly Detection Self Supervised Anomaly

October 1, 2023

Don't Miss Out on Novelty: Importance of Novel Features for Deep Anomaly Detection
Sarath Sivaprasad, Mario Fritz
Anomaly Detection Importance Aware Novelty Search Deep Anomaly Detection Pixel Level Anomaly Anomaly Detection Benchmark New Feature Anomaly Type

September 27, 2023

ADGym: Design Choices for Deep Anomaly Detection
Minqi Jiang, Chaochuan Hou, Ao Zheng, Songqiao Han, Hailiang Huang, Qingsong Wen, Xiyang Hu, Yue Zhao
Deep Learning Anomaly Detection Deep Anomaly Detection Design Choice

September 18, 2023

An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination
Minkyung Kim, Jongmin Yu, Junsik Kim, Tae-Hyun Oh, Jun Kyun Choi
Unsupervised Anomaly Detection Data Contamination Deep Anomaly Detection Anomaly Detection Model Iterative Method Anomaly Detection Benchmark

July 4, 2023

Prototypes as Explanation for Time Series Anomaly Detection
Bin Li, Carsten Jentsch, Emmanuel Müller
Anomaly Detection Line by Line Explanation Black Box Black Box Model Visual Prototype Deep Anomaly Detection

May 25, 2023

Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning
Hongzuo Xu, Yijie Wang, Juhui Wei, Songlei Jian, Yizhou Li, Ning Liu
Anomaly Detection Based Anomaly Detection Deep Anomaly Detection Deep Supervision Supervision Signal

May 24, 2023

Beyond Individual Input for Deep Anomaly Detection on Tabular Data
Hugo Thimonier, Fabrice Popineau, Arpad Rimmel, Bich-Liên Doan
Anomaly Detection Tabular Data Anomaly Score Tabular Datasets Deep Anomaly Detection Non Autoregressive Transformer

April 15, 2023

Context-aware Domain Adaptation for Time Series Anomaly Detection
Kwei-Herng Lai, Lan Wang, Huiyuan Chen, Kaixiong Zhou, Fei Wang, Hao Yang, Xia Hu
Deep Anomaly Detection Time Series Domain Adaptation

March 10, 2023

Deep Anomaly Detection on Tennessee Eastman Process Data
Fabian Hartung, Billy Joe Franks, Tobias Michels, Dennis Wagner, Philipp Liznerski, Steffen Reithermann, Sophie Fellenz, Fabian Jirasek, Maja Rudolph, Daniel Neider, Heike Leitte, Chen Song, Benjamin Kloepper, Stephan Mandt, Michael Bortz, Jakob Burger, Hans Hasse, Marius Kloft
Anomaly Detection Deep Anomaly Detection Industrial Application

February 15, 2023

February 13, 2023

December 8, 2022

On Root Cause Localization and Anomaly Mitigation through Causal Inference
Xiao Han, Lu Zhang, Yongkai Wu, Shuhan Yuan
Anomaly Detection Causal Inference Causal Direction Root Cause Deep Anomaly Detection