Anomaly Detection Performance

Anomaly detection research focuses on accurately identifying unusual patterns in data, aiming to improve the efficiency and reliability of various systems. Current efforts concentrate on developing robust models, including autoencoders, graph neural networks, and transformers, often incorporating techniques like dimensionality reduction, counterfactual augmentation, and ensemble methods to enhance performance across diverse data types (e.g., images, time series, tabular data, graphs). These advancements are crucial for applications ranging from predictive maintenance in industrial settings to cybersecurity and healthcare, enabling timely interventions and improved decision-making. The field is also actively exploring methods to improve model interpretability and address challenges like data imbalance and the need for efficient, generalizable solutions.

Papers

November 1, 2024

KAN-AD: Time Series Anomaly Detection with Kolmogorov-Arnold Networks
Quan Zhou, Changhua Pei, Fei Sun, Jing Han, Zhengwei Gao, Dan Pei, Haiming Zhang, Gaogang Xie, Jianhui Li
Anomaly Detection Black Box Kolmogorov Arnold Network Anomaly Detection Performance

October 8, 2024

MTFL: Multi-Timescale Feature Learning for Weakly-Supervised Anomaly Detection in Surveillance Videos
Yiling Zhang, Erkut Akdag, Egor Bondarev, Peter H. N. De With
Feature Learning Surveillance Video Video Anomaly Anomaly Detection Performance Weakly Supervised Anomaly Detection Spatial Temporal Video

October 2, 2024

Incorporating Metabolic Information into LLMs for Anomaly Detection in Clinical Time-Series
Maxx Richard Rahman, Ruoxuan Liu, Wolfgang Maass
Anomaly Detection Medical LLM Anomaly Detection Performance Clinical Time Series Metabolic Network

September 16, 2024

Enhancing Anomaly Detection via Generating Diversified and Hard-to-distinguish Synthetic Anomalies
Hyuntae Kim, Changhee Lee
Anomaly Detection Unsupervised Anomaly Detection Anomaly Detection Performance Synthetic Anomaly

July 13, 2024

Imbalanced Graph-Level Anomaly Detection via Counterfactual Augmentation and Feature Learning
Zitong Wang, Xuexiong Luo, Enfeng Song, Qiuqing Bai, Fu Lin
Graph Neural Network Feature Learning Anomaly Detection Performance Anomalous Graph Graph Level Anomaly Detection Counterfactual Augmentation

June 1, 2024

Towards a Unified Framework of Clustering-based Anomaly Detection
Zeyu Fang, Ming Gu, Sheng Zhou, Jiawei Chen, Qiaoyu Tan, Haishuai Wang, Jiajun Bu
Anomaly Detection Unified Framework Unsupervised Anomaly Detection Anomaly Score Anomaly Detection Performance Anomaly Clustering

May 27, 2024

ARC: A Generalist Graph Anomaly Detector with In-Context Learning
Yixin Liu, Shiyuan Li, Yu Zheng, Qingfeng Chen, Chengqi Zhang, Shirui Pan
Anomaly Detection Context Learning Node Embeddings Graph Anomaly Detection Anomaly Detection Performance Anomalous Graph

April 24, 2024

S2DEVFMAP: Self-Supervised Learning Framework with Dual Ensemble Voting Fusion for Maximizing Anomaly Prediction in Timeseries
Sarala Naidu, Ning Xiong
Anomaly Detection Time Series Anomaly Detection Performance Self Supervised Learning Framework Voting Ensemble

April 16, 2024

CARE to Compare: A real-world dataset for anomaly detection in wind turbine data
Christian Gück, Cyriana M. A. Roelofs, Stefan Faulstich
Anomaly Detection Fault Detection Wind Power Real World Dataset CaRE SD Anomaly Detection Performance Anomaly Detection Model

March 17, 2024

Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning
Xiaohao Xu, Yunkang Cao, Yongqi Chen, Weiming Shen, Xiaonan Huang
Anomaly Detection Complex Reasoning Anomaly Detection Performance Language Foundation Model

March 7, 2024

Exploring the Influence of Dimensionality Reduction on Anomaly Detection Performance in Multivariate Time Series
Mahsun Altin, Altan Cakir
Anomaly Detection Dimensionality Reduction Multivariate Time Series External Influence Anomaly Detection Performance Unsupervised Time Series Anomaly Detection Transformer Based Anomaly Detection

March 4, 2024

Towards efficient deep autoencoders for multivariate time series anomaly detection
Marcin Pietroń, Dominik Żurek, Kamil Faber, Roberto Corizzo
Deep Learning Multivariate Time Series Anomaly Detection Anomaly Detection Performance Neural Network Autoencoder Anomaly Detection Benchmark

December 30, 2023

Enabling Smart Retrofitting and Performance Anomaly Detection for a Sensorized Vessel: A Maritime Industry Experience
Mahshid Helali Moghadam, Mateusz Rzymowski, Lukasz Kulas
Interpretable Model Interpretable Machine Learning Anomaly Detection Performance Port Operation Deep Learning Based Anomaly Detection Maritime Industry Freight Carrying Vessel

December 3, 2023

ADT: Agent-based Dynamic Thresholding for Anomaly Detection
Xue Yang, Enda Howley, Micheal Schukat
Anomaly Detection Automatic Thresholding Anomaly Detection Performance

August 28, 2023

Neural Network Training Strategy to Enhance Anomaly Detection Performance: A Perspective on Reconstruction Loss Amplification
YeongHyeon Park, Sungho Kang, Myung Jin Kim, Hyeonho Jeong, Hyunkyu Park, Hyeong Seok Kim, Juneho Yi
Neural Network Unsupervised Anomaly Detection Visual Perspective Anomaly Sample Anomaly Detection Performance Reconstruction Loss Reconstruction Metric

July 2, 2023

3D-IDS: Doubly Disentangled Dynamic Intrusion Detection
Chenyang Qiu, Yingsheng Geng, Junrui Lu, Kaida Chen, Shitong Zhu, Ya Su, Guoshun Nan, Can Zhang, Junsong Fu, Qimei Cui, Xiaofeng Tao
Network Intrusion Detection Anomaly Detection Performance Unknown Attack Feature Space Hijacking Attack

June 12, 2023

No Free Lunch: The Hazards of Over-Expressive Representations in Anomaly Detection
Tal Reiss, Niv Cohen, Yedid Hoshen
Anomaly Detection Interpretable Representation Free Lunch Anomaly Detection Performance Image Anomaly Detection Expressivity Transfer Sufficient Representation Hazard Triggering Event

May 22, 2023

AD-MERCS: Modeling Normality and Abnormality in Unsupervised Anomaly Detection
Jonas Soenen, Elia Van Wolputte, Vincent Vercruyssen, Wannes Meert, Hendrik Blockeel
Anomaly Detection Unsupervised Anomaly Detection UNsupervised Approach Anomaly Detection Performance Anomaly Detector Evident Abnormality

May 17, 2023

Reconstruction Error-based Anomaly Detection with Few Outlying Examples
Fabrizio Angiulli, Fabio Fassetti, Luca Ferragina
Anomaly Detection Supervised Autoencoder Anomaly Detection Performance Semi Supervised Anomaly Detection Reconstruction Based Anomaly Detection

April 30, 2023

SLSG: Industrial Image Anomaly Detection by Learning Better Feature Embeddings and One-Class Classification
Minghui Yang, Jing Liu, Zhiwei Yang, Zhaoyang Wu
Anomaly Detection Graph Convolutional Network Feature Embeddings One Class Classification Anomaly Detection Performance Industrial Image Anomaly Detection

Anomaly Detection Performance

Papers

KAN-AD: Time Series Anomaly Detection with Kolmogorov-Arnold Networks

MTFL: Multi-Timescale Feature Learning for Weakly-Supervised Anomaly Detection in Surveillance Videos

Incorporating Metabolic Information into LLMs for Anomaly Detection in Clinical Time-Series

Enhancing Anomaly Detection via Generating Diversified and Hard-to-distinguish Synthetic Anomalies

Imbalanced Graph-Level Anomaly Detection via Counterfactual Augmentation and Feature Learning

Towards a Unified Framework of Clustering-based Anomaly Detection

ARC: A Generalist Graph Anomaly Detector with In-Context Learning

S2DEVFMAP: Self-Supervised Learning Framework with Dual Ensemble Voting Fusion for Maximizing Anomaly Prediction in Timeseries

CARE to Compare: A real-world dataset for anomaly detection in wind turbine data

Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning

Exploring the Influence of Dimensionality Reduction on Anomaly Detection Performance in Multivariate Time Series

Towards efficient deep autoencoders for multivariate time series anomaly detection

Enabling Smart Retrofitting and Performance Anomaly Detection for a Sensorized Vessel: A Maritime Industry Experience

ADT: Agent-based Dynamic Thresholding for Anomaly Detection

Neural Network Training Strategy to Enhance Anomaly Detection Performance: A Perspective on Reconstruction Loss Amplification

3D-IDS: Doubly Disentangled Dynamic Intrusion Detection

No Free Lunch: The Hazards of Over-Expressive Representations in Anomaly Detection

AD-MERCS: Modeling Normality and Abnormality in Unsupervised Anomaly Detection

Reconstruction Error-based Anomaly Detection with Few Outlying Examples

SLSG: Industrial Image Anomaly Detection by Learning Better Feature Embeddings and One-Class Classification