Anomaly Detection
Anomaly detection focuses on identifying unusual patterns or deviations from expected behavior within data, aiming to improve system reliability and safety across diverse applications. Current research emphasizes unsupervised and self-supervised learning approaches, employing architectures like autoencoders, transformers, and graph neural networks, often incorporating techniques such as Bayesian inference and metric learning to enhance robustness and interpretability. The field's significance stems from its broad applicability, ranging from fraud detection and medical diagnosis to industrial process monitoring and network security, with ongoing efforts to develop more efficient, accurate, and explainable methods.
Papers
Driving Anomaly Detection Using Conditional Generative Adversarial Network
Yuning Qiu, Teruhisa Misu, Carlos Busso
Practical data monitoring in the internet-services domain
Nikhil Galagali
A Framework for Verifiable and Auditable Federated Anomaly Detection
Gabriele Santin, Inna Skarbovsky, Fabiana Fournier, Bruno Lepri
Transfer Learning as an Essential Tool for Digital Twins in Renewable Energy Systems
Chandana Priya Nivarthi
Anomaly Detection for Unmanned Aerial Vehicle Sensor Data Using a Stacked Recurrent Autoencoder Method with Dynamic Thresholding
Victoria Bell1, Divish Rengasamy, Benjamin Rothwell, Grazziela P Figueredo
The Familiarity Hypothesis: Explaining the Behavior of Deep Open Set Methods
Thomas G. Dietterich, Alexander Guyer
Exploring Scalable, Distributed Real-Time Anomaly Detection for Bridge Health Monitoring
Amirhossein Moallemi, Alessio Burrello, Davide Brunelli, Luca Benini
Abuse and Fraud Detection in Streaming Services Using Heuristic-Aware Machine Learning
Soheil Esmaeilzadeh, Negin Salajegheh, Amir Ziai, Jeff Boote