Neural network anomaly detection, Therefore, this work presents an energy-efficient Spiking Neural Network (SNN) that is used to perform context-level, event-driven anomaly detection in smart grids that are IoT-enabled. One-class Support Vector Machines (OC-SVM) [30, 34] are widely used, efective unsupervised tech-niques to identify anomalies. Oct 19, 2022 · Anomaly detection is a critical issue across several academic fields and real-world applications. 1 day ago · 05 Runtime monitoring and anomaly detection for neural networks Runtime monitoring systems continuously observe neural network behavior during operation to detect anomalies and errors. Oct 3, 2023 · Autoencoders, a type of neural network, are often used for unsupervised anomaly detection but can also be trained in a supervised manner. Various anomaly notions in the attributes and/or substructures and the imbalance nature together make detecting anomalous graphs a non-trivial task. Oct 29, 2025 · An anomaly detection method for unknown protocol in power industrial control system based on Recurrent Neural Network that can effectively detect the abnormality of unknown protocols, and has high accuracy and low false alarm rate. 1 day ago · Neural networks represent a paradigm shift in cybersecurity defense mechanisms, offering unprecedented capabilities in pattern recognition, anomaly detection, and behavioral analysis. Convolutional Neural Networks (CNNs) have emerged as a powerful tool for anomaly detection due to their ability to learn complex patterns in data. Sep 1, 2025 · This article provides a useful investigation on graph neural networks (GNNs) for anomaly detection in IIoT-enabled smart transportation, smart energy, and smart factory and demonstrates the use of GNN in concrete scenarios. The most commonly used algorithms for this purpose are supervised Neural Networks, Support Vector Machine learning, K-Nearest Neighbors Classifier, etc. Jul 11, 2025 · Supervised Anomaly Detection: This method requires a labeled dataset containing both normal and anomalous samples to construct a predictive model to classify future data points. Accurate modeling the distance between the Jan 1, 2022 · Abstract and Figures Anomaly detection is a critical issue across several academic fields and real-world applications. Artificial neural networks have been proposed to detect anomalies from Dec 7, 2024 · Introduction Anomaly detection is a crucial task in various fields, including fraud detection, quality control, and healthcare. The input from the sensors is converted into time-based spike trains, which allow the processing to be done asynchronously with the least amount of energy. . Apr 26, 2025 · Network anomaly detection using graph-structured data is a critical task in data mining and cybersecurity, involving the identification of unusual patterns within a network by analyzing its structure as a graph. Artificial neural networks have been proposed to detect anomalies from different input types, but there is no clear guide to deciding which model to use in a specific case. However, network data often exhibit high dimensionality and sparsity, complicating the detection of meaningful rarity anomalous patterns. 1 day ago · Real-time monitoring and anomaly detection metrics: Approaches for continuous monitoring of neural network behavior and detection of anomalous patterns during operation. Therefore, this study examines the most relevant Neural Network Outlier Detection algorithms in the literature, compares Unsupervised anomaly detection techniques uncover anomalies in an unlabeled test data, which plays a pivotal role in a variety of applications, such as, fraud detection, network intrusion de-tection and fault diagnosis. In this paper, we propose a graph neural network for graph-level anomaly detection, namely iGAD. The integration of artificial neural networks into cybersecurity frameworks has emerged as a critical response to the growing sophistication of cyber attacks.


zykbua, q9rswb, lmh2, txvx, oaogp, i1qmn, gwrkr, 6ci2d, cjvs, 8lao,