Kyusuk Han

The exponential growth of autonomous systems demands robust security mechanisms that can operate within the extreme constraints of real-time embedded environments. This paper introduces SMART DShot, a groundbreaking machine learning-enhanced framework that transforms the security landscape of unmanned aerial vehicle motor control systems through seamless integration of adaptive timing correction and real-time anomaly detection within Digital Shot (DShot) communication protocols. Our approach addresses critical vulnerabilities in Electronic Speed Controller (ESC) interfaces by deploying four synergistic algorithms—Kalman Filter Timing Correction (KFTC), Recursive Least Squares Timing Correction (RLSTC), Fuzzy Logic Timing Correction (FLTC), and Hybrid Adaptive Timing Correction (HATC)—each optimized for specific error characteristics and attack scenarios. Through comprehensive evaluation encompassing 32,000 Monte Carlo test iterations (500 per scenario × 16 scenarios × 4 algorithms) across 16 distinct operational scenarios and PolarFire SoC Field-Programmable Gate Array (FPGA) implementation, we demonstrate exceptional performance with 88.3% attack detection rate, only 2.3% false positive incidence, and substantial vulnerability mitigation reducing Common Vulnerability Scoring System (CVSS) severity from High (7.3) to Low (3.1). Hardware validation on PolarFire SoC confirms practical viability with minimal resource overhead (2.16% Look-Up Table utilization, 16.57 mW per channel) and deterministic sub-10 microsecond execution latency. The Hybrid Adaptive Timing Correction algorithm achieves 31.01% success rate (95% CI: [30.2%, 31.8%]), representing a 26.5% improvement over baseline approaches through intelligent meta-learning-based algorithm selection. Statistical validation using Analysis of Variance confirms significant performance differences (F(3,1996) = 30.30, p < 0.001) with large effect sizes (Cohen’s d up to 4.57), where 64.6% of algorithm comparisons showed large practical significance. SMART DShot establishes a paradigmatic shift from reactive to proactive embedded security, demonstrating that sophisticated artificial intelligence can operate effectively within microsecond-scale real-time constraints while providing comprehensive protection against timing manipulation, de-synchronization, burst interference, replay attacks, coordinated multi-channel attacks, and firmware-level compromises. This work provides essential foundations for trustworthy autonomous systems across critical domains including aerospace, automotive, industrial automation, and cyber–physical infrastructure. These results conclusively demonstrate that ML-enhanced motor control systems can achieve both superior security (88.3% attack detection rate with 2.3% false positives) and operational performance (31.01% timing correction success rate, 26.5% improvement over baseline) simultaneously, establishing SMART DShot as a practical, deployable solution for next-generation autonomous systems.

Digital Twin (DT) aims to seamlessly replicate physical objects or processes in virtual environments, garnering attention for supporting diverse intelligent management services such as monitoring, analysis, and control. Integration with technologies like artificial intelligence (AI), big data, edge computing, and the Internet of Things (IoT) has propelled the development of DTs. However, the DT may not only introduce new potential security flaws but also inherit existing vulnerabilities from the technologies they incorporate and interact with due to their integration with diverse technologies. Despite its growing impact, research addressing the security concerns of DTs remains insufficient and still in its early stages. In this article, we provide a comprehensive and in-depth review of the current state of DTs, focusing on their security aspects. We first depict an overview of DTs, including the definition of the DT and various DT applications, and then present the architecture for DTs. Subsequently, we conduct a detailed examination of security attacks and threats across the functional layers of the DT architecture. In contrast to the previous surveys on DTs, we derive security properties and security functional requirements (SFRs) based on the Common Criteria (CC) standard for mitigating these attacks and threats. We also introduce technologies that enable the achievement of SFRs with a future research perspective. By addressing these critical security aspects, our article enhances the security and trustworthiness of DTs, contributing to their safe and reliable deployment in various domains.

The drone swarm is a preferable way to deploy many drones for large-scale missions. Establishing secure communication among drones in drone swarms is essential as the fog drone controls all other edge drones in the swarm. Although many researchers proposed methods of authenticating drones, most of them are unsuitable for use in swarm environments as they require either the ground station during the authentication or expensive PKI-based crypto operations with limited flexibility and scalability. In this work, we propose an efficient and scalable authentication protocol for drone swarm environments, enabling mutual authentication between fog and edge drones without involving the ground station. Moreover, we show that the protocol enables the verification of the sender in group communication. Protocol evaluations show security requirements satisfaction while achieving 14 - 20 times less computation overhead as compared to PKI-based models.​​

The concern about cyber threats on unmanned aerial vehicles (UAVs) increases as they become more sophisticated and widely used in various areas. Although there have been efforts to improve the security of UAVs, their focus is limited to physical attacks and securing communication, and many areas remain open to issues. Although a more comprehensive approach is required to improve the overall areas of UAVs, it is reasonable to investigate the case study from the perspective of other similar cyber-physical systems (CPSs). Thus, we see the architectural similarity between UAVs and automobiles. Automotive security has seen significant improvement throughout the last decade as vehicles have begun to have connectivity and autonomy. There have been extensive research and development efforts in various aspects, including securing the components, securing communications, securing software updates, and securing the overall management system to provide multi-layered security for the automotive environments, and standardization and regulations are being issued. Due to the similarity, the employment of ideas from the automotive environments in the UAV environments becomes a reasonable approach. In this paper, we show the automotive security trends and discuss how UAV environments are comparable to automotive environments. We then show how security in automotives is adapted in UAVs with a case study.

As automotive embedded systems comprised of electronic control units (ECUs) connected via a controller area network (CAN) have continued to develop, the volume of information these systems are required to handle has also rapidly increased. Cyber attacks targeting vulnerable points of automotive embedded systems in particular are on the rise to hinder normal operation of a vehicle. However, adding security mechanisms to defend against attacks cannot neglect timing requirements in terms of vehicle safety. This is because it may lead to a violation of automobile safety. In short, both sides of this issue must be addressed from the outset of the system design stage to provide optimal security and safety. As a response to this pressing issue, we propose a novel and efficient scheme. The design optimization during the system design phase not only ensures all the real-time applications are executed within their deadline but also reduces the number of transmitted messages over the CAN bus. After optimization, we apply a hash message authentication code (HMAC) to specific messages, providing secure communication between ECUs and protecting against cyber attacks. Security analysis and experimental results prove that the proposed scheme can counter attacks on the CAN bus while meeting timing requirements. Therefore, our proposed scheme is effective in satisfying improvement of both safety and security.