Local-Global Routing Between Capsules for Hyperspectral Image Classification With Noisy Labels

Digital Signal Processing, Год журнала: 2025, Номер unknown, С. 105294 - 105294

Опубликована: Май 1, 2025

Язык: Английский

---

Maximum correntropy criterion-based Kalman filter for replay attack in non-Gaussian noises

Signal Processing, Год журнала: 2025, Номер unknown, С. 110098 - 110098

Опубликована: Май 1, 2025

Язык: Английский

---

Securing electric transportation networks: A machine learning-driven cyber threat detection

MATEC Web of Conferences, Год журнала: 2024, Номер 392, С. 01184 - 01184

Опубликована: Янв. 1, 2024

The study examines the cybersecurity environment of electric transportation networks using a machine learning-based methodology. It analyzes behaviors vehicles, charging patterns, cyber threat occurrences, and performance learning models. An analysis vehicle (EV) data shows that there are differences in battery capacity distances covered, suggesting presence possible weaknesses across different cars. Cyber logs provide comprehensive view various levels severity time it takes to discover them, illustrating ever-changing nature threats network. Machine models have varying performance; ML003 ML005 exhibit excellent accuracy precision identification, whilst ML002 significantly lower metrics. These results highlight need implementing flexible solutions handle effectively reduce risks. This research emphasizes proactive detection tactics order address high-severity attacks. also highlights for ongoing improvement strengthen network security. enhances our comprehension obstacles networks, highlighting crucial significance strengthening resilience against threats.

Язык: Английский

---

A Review and Analysis of Attack and Countermeasure Approaches for Enhancing Smart Grid Cybersecurity

Опубликована: Апрель 23, 2024

Язык: Английский

---

Blockchain for Energy Market: A Comprehensive Survey

Sustainable Energy Grids and Networks, Год журнала: 2024, Номер unknown, С. 101614 - 101614

Опубликована: Дек. 1, 2024

Язык: Английский

---

Detection of Cyber-Attacks and Power Disturbances in Smart Digital Substations using Continuous Wavelet Transform and Convolution Neural Networks

Electric Power Systems Research, Год журнала: 2024, Номер 229, С. 110157 - 110157

Опубликована: Янв. 24, 2024

Язык: Английский

---

Reinforcing Network Security: Network Attack Detection Using Random Grove Blend in Weighted MLP Layers

Mathematics, Год журнала: 2024, Номер 12(11), С. 1720 - 1720

Опубликована: Май 31, 2024

In the modern world, evolution of internet supports automation several tasks, such as communication, education, sports, etc. Conversely, it is prone to types attacks that disturb data transfer in network. Efficient attack detection needed avoid consequences an attack. Traditionally, manual limited by human error, less efficiency, and a time-consuming mechanism. To address problem, large number existing methods focus on techniques for better efficacy detection. However, improvement significant factors accuracy, handling larger data, over-fitting versus fitting, tackle this issue, proposed system utilized Random Grove Blend Weighted MLP (Multi-Layer Perceptron) Layers classify network attacks. The used its advantages solving complex non-linear problems, datasets, high accuracy. computation requirements great deal labeled training data. resolve random info grove blend weight weave layer are incorporated into attain this, UNSW–NB15 dataset, which comprises nine attack, detect Moreover, Scapy tool (2.4.3) generate real-time dataset classifying efficiency presented mechanism calculated with performance metrics. Furthermore, internal external comparisons processed respective research reveal system’s efficiency. model utilizing attained accuracy 98%. Correspondingly, intended contribute associated enhancing security.

Язык: Английский

---

Distributed Photovoltaic Communication Anomaly Detection Based on Spatiotemporal Feature Collaborative Modeling

Applied Sciences, Год журнала: 2024, Номер 14(21), С. 9820 - 9820

Опубликована: Окт. 27, 2024

As distributed photovoltaic (PV) technology rapidly develops and is widely applied, the methods of cyberattacks are continuously evolving, posing increasingly severe threats to communication networks PV systems. Recent studies have shown that Transformer model, which effectively integrates global information handles long-distance dependencies, has garnered significant attention. Based on this, our research proposes a model named STformer, applied task attack detection in communication. Specifically, we propose temporal attention mechanism variable mechanism. The focuses capturing subtle changes trends data sequences over time, ensuring highly sensitive recognition patterns inherent time-series data. In contrast, analyzes intrinsic relationships interactions between different variables, uncovering critical correlations may indicate abnormal behavior or potential attacks. Additionally, incorporate Uniform Manifold Approximation Projection (UMAP) dimensionality reduction technique. This technique not only helps reduce computational complexity but, certain cases, can enhance anomaly performance. Finally, compared classical advanced methods, STformer demonstrates satisfactory performance simulation experiments.

Язык: Английский

---

Research on User Abnormal Behavior Recognition Model for Water Economy Operating System Based on Transformer

Опубликована: Июнь 21, 2024

Язык: Английский

---