Unmanned Aerial Vehicles (UAVs) have demonstrated significant capabilities across various applications, including logistics, urban air mobility, surveillance, and defense. However, UAV operational effectiveness heavily depends on the Global Positioning System (GPS), which provides real-time navigation essential for mission success. UAV reliance on GPS introduces potential vulnerabilities to spoofing attacks, where adversaries transmit fictitious signals to disrupt navigation. This study proposes RLDM-UAV (Reinforcement Learning-driven integrated Detection and Mitigation of UAV GPS spoofing attacks), a novel reinforcement learning framework integrating detection and mitigation to ensure resilient UAV navigation. RLDM-UAV relies on GPS data and onboard camera inputs, eliminating the need for additional sensors. RLDM-UAV utilizes a Deep Q-Network (DQN)-based algorithm to enable dynamic GPS spoofing detection and adaptive switching between GPS-based and vision-based navigation policies based on the reliability of GPS signals. To enhance learning efficiency, we propose a novel experience replay mechanism that prioritizes incorrect detections. The average online computation time for the real-time detection and mitigation decision per time step is less than 23 ms on ARM-based CPUs. The performance of RLDM-UAV is evaluated against three types of GPS spoofing attacks: random attacks, replay attacks, and stealth attacks. The results demonstrate that RLDM-UAV achieves superior attack detection accuracies across all three types of GPS spoofing attacks and greater robustness under varying attack rates during testing compared to baseline methods.

Enhancing cybersecurity in DC shipboard microgrid (SMG) systems is crucial for maintaining the resilience of energy operation in maritime transportation systems (MTS). However, increasing cyber threats pose significant challenges to deploying resilient technologies in intelligent DC SMGs. These intricate cyber-physical systems, comprising power electronics, distributed generation units, sensors, and monitoring technologies, are managed remotely, making them vulnerable to attacks that jeopardize their stability and security. Existing solutions often require additional support due to low detection and high false alarm rates, primarily from manual analysis. To address these issues, this study presents a sophisticated deep learning-driven cyber-attack detection and identification model designed to effectively enhance the security of DC SMGs in MTS. The proposed framework leverages Long Short-Term Memory (LSTM) with variational autoencoder (VAE) architectures for deep feature extraction (DFE) under attack scenarios. VAE schemes automatically uncover hidden patterns within the DC SMG network, and their outputs are utilized by deep learning (DL) schemes for accurate attack detection. The proposed model incorporates a deep artificial neural network (ANN)-based encoder-decoder scheme to identify attacks in DC SMGs, contributing to an efficient operation. Additionally, DL-based LSTM-VAE and ANN are meticulously designed with appropriate hyperparameters to counter cyber threats. The data-driven DL method achieved the testing accuracy of 99.81%, outperforming various state-of-the-art (SOTA) DL and machine learning (ML) methods. Extensive testing scenarios have been conducted to demonstrate the performance and robustness of the proposed DL methods under different levels of attacks, ensuring their efficacy in enhancing the cybersecurity of DC shipboard microgrids.

In the ever-evolving realm of network security, the swift and accurate identification of diverse attack classes within network traffic is of paramount importance. This paper introduces “ByteStack-ID,” a pioneering approach tailored for packet-level intrusion detection. At its core, ByteStack-ID leverages grayscale images generated from the frequency distributions of payload data, a groundbreaking technique that greatly enhances the model's ability to discern intricate data patterns. Notably, our approach is exclusively grounded in packet-level information, a departure from conventional Network Intrusion Detection Systems (NIDS) that predominantly rely on flow-based data. While building upon the fundamental concept of stacking methodology, ByteStack-ID diverges from traditional stacking approaches. It seamlessly integrates additional meta learner layers into the concatenated base learners, creating a highly optimized, unified model. Empirical results unequivocally confirm the outstanding effectiveness of the ByteStack-ID framework, consistently outperforming baseline models and state-of-the-art approaches across pivotal performance metrics, including precision, recall, and F1-score. Impressively, our proposed approach achieves an exceptional 81% macro F1-score in multiclass classification tasks. In a landscape marked by the continuous evolution of network threats, ByteStack-ID emerges as a robust and versatile security solution, relying solely on packet-level information extracted from network traffic data.

Adapting modern approaches for network intrusion detection is becoming critical, given the rapid technological advancement and adversarial attack rates. Therefore, packet-based methods utilizing payload data are gaining much popularity due to their effectiveness in detecting certain attacks. However, packet-based approaches suffer from a lack of standardization, resulting in incomparability and reproducibility issues. Unlike flow-based datasets, no standard labeled dataset exists, forcing researchers to follow bespoke labeling pipelines for individual approaches. Without a standardized baseline, proposed approaches cannot be compared and evaluated with each other. One cannot gauge whether the proposed approach is a methodological advancement or is just being benefited from the proprietary interpretation of the dataset. Addressing comparability and reproducibility issues, we introduce Payload-Byte, an open-source tool for extracting and labeling network packets in this work. Payload-Byte utilizes metadata information and labels raw traffic captures of modern intrusion detection datasets in a generalized manner. Moreover, we transformed the labeled data into a byte-wise feature vector that can be utilized for training machine learning models. The whole cycle of processing and labeling is explicitly stated in this work. Furthermore, source code and processed data are made publicly available so that it may act as a standardized baseline for future research work. Lastly, we present a brief comparative analysis of machine learning models trained on packet-based and flow-based data.

Microgrids specialized for tactical operations have been subjected to several challenges. These tactical power networks are islanded and have a relatively low power generation capacity. Meeting power requirements of military equipment, having intermittent and highly inductive nature, exposes microgrids to severe stresses. Existing methodologies to monitor and control the impact of load variations require sophisticated equipment and trained personnel. The objective of this research paper is to present an open-source edge energy monitoring system (EEMS) for efficient demand management of tactical networks. The proposed system is capable of capturing all minute operational artifacts, including harmonic distortions and power quality of these networks. A variable gain amplifier circuit enables the proposed EMS to sense all the signals in a wide range of power with higher resolution. The proposed system utilizes raspberry pi as an edge device to meet the low power requirements of tactical networks. The novel concurrent programming approach adopted in the proposed EMS, effectively handles the large amount of data acquired from the network. This parallel processing of acquired data speeds up the execution process. All electrical parameters obtained during this process are stored in an encrypted local database that can be utilized for fault analysis and load prediction. Further integration of machine learning tools in proposed EMS assists in automated power network reconfiguration and tuning under harsh battlefield situations.

Unmanned aircraft systems (UAS) have emerged as a useful aid for entertainment, monitoring, and defense activities. A Significant research effort is being invested in UASs to increase the payload capacity and monitoring/processing capabilities. To achieve this, the power density of UAS must be increased. In conventional UAS, for starting the fuel-powered engine, an engine starter is usually used. Once the engine starts, the engine torque is used for driving an alternator, which powers the electrical power system (EPS) of the UAS. This paper presents a novel axial-flux machine-based motor-generator system (MGS), capable to operate as an engine starter thereby eliminating the external starter. The design is targeted to meet the specifications given in the US Army SBIR, to achieve a continuous power density of 3kW/kg for a 7kW power rating. Additionally, the design also meets the dimensional requirements, required to fit with the existing engine. The compact power converter design and control also compliment the motor-generator design. The necessary design steps, and control algorithm to support bidirectional flow are discussed in detail. Finally, detailed simulation results verifying the performance requirement during engine start, generation mode, and emergency mode are also presented.

In the existing power system architecture of military aircraft (such as F-35), electrical loads are fed from two 270V-HVDC buses. These two HVDC buses are completely isolated from each other. In existing architecture, there is no possibility of power transfer between the two buses. This inability reflects as overdesigning of the system to meet the dynamic loads and possible power quality deterioration during operation (occurring due to unequal loading of the two HVDC buses). This paper attempts to address this inability by introducing the concept of dynamic power balancing between the buses. As military aircraft design criteria are sensitive to weight and size, the introduction of the proposed feature must not add additional weight to the system. To ensure this, the authors have studied the existing architecture and have attempted to replace the two 270V to 28V Dual-Active Bridge (DAB) converter (used for charging the 28V battery) with the proposed Triple-Active Bridge (TAB) converter. This converter must be capable of achieving power balancing in addition to the conventional 28V battery charging operation. To achieve this, a modulation strategy to achieve bidirectional power flow and soft-switching is also discussed. Simulation results verifying the feasibility of the proposed converter and control are also presented.

This paper presents an improved secondary voltage control (SVC) methodology incorporating compressive sensing (CS) for a multiarea power system. SVC minimizes the voltage deviation of the load buses while CS deals with the problem of the limited bandwidth capacity of the communication channel by reducing the size of massive data output from the phasor measurement unit (PMU) based monitoring system. The proposed strategy further incorporates the application of a morphological median filter (MMF) to reduce noise from the output of the PMUs. To keep the control area secure and protected locally, mathematical singular entropy (MSE) based fault identification approach is utilized for fast discovery of faults in the control area. Simulation results with 27-bus and 486-bus power systems show that CS can reduce the data size up to 1/10th while the MSE-based fault identification technique can accurately distinguish between fault and steady-state conditions.