As the importance of cyber security for nuclear power plants has recently increased, related organizations such as manufactures, operators, regulators and research institutes have taken into consideration the many concerns for effective application of cyber security to critical digital assets at nuclear power plants. It is essential to analyze and research how to effectively apply nuclear cyber security requirements and what complementary factors are present in the overall process for a nuclear security technology system. The complementary points of nuclear cyber security technology could be analyzed through diverse cyber security methods such cyber security assurance, assessments, and software development life cycle. It is necessary to apply nuclear cyber security technology effectively in accordance with the operation, assurance and system development process of a nuclear facility. These analysis results could be applied to technical points for the cyber security of critical digital assets at nuclear power plants in the future and to technology that needs to be at the appropriate level of cyber security to ensure technical assurance. This paper is a new approach to compare and analyze various methods used in the cyber security field to discover complementary points for the application of cyber security to critical systems in nuclear power plants. Additionally, this paper also presents effective methods for developing and applying, evaluating, and regulating cyber security in nuclear digital critical systems using the complementary points of various cyber security methods identified in the analysis.

Instrumentation and Control (I&C) systems of nuclear power plants (NPPs) have been continuously digitalized. These systems have a critical role in the operation of nuclear facilities by functioning as the brain of NPPs. In recent years, as cyber security threats to NPP systems have increased, regulatory and policy-related organizations around the world, including the International Atomic Energy Agency (IAEA), Nuclear Regulatory Commission (NRC) and Korea Institute of Nuclear Nonproliferation and Control (KINAC), have emphasized the importance of nuclear cyber security by publishing cyber security guidelines and recommending cyber security requirements for NPP facilities. As described in NRC Regulatory Guide (Reg) 5.71 and KINAC RS015, challenge response authentication should be applied to the critical digital I&C system of NPPs to satisfy the cyber security requirements. There have been no cases in which the most robust response authentication technology like challenge response has been developed and applied to nuclear I&C systems. This paper presents a challenge response authentication mechanism for a Programmable Logic Controller (PLC) system used as a control system in the safety system of the Advanced Power Reactor (APR) 1400 NPP.

As Controller Area Network (CAN) Intrusion Detection Systems (IDS) become increasingly sophisticated and incorporate deep learning architectures, adversarial attacks have evolved correspondingly over the past decade. To assess the vulnerability of deep learning-based CAN IDS to evasion attacks, we developed a Double Deep Q-Network (DDQN) agent capable of performing adversarial attacks against two critical attack types: Denial of Service (DoS) and Fuzzing attacks. Our methodology employs reinforcement learning to systematically discover perturbation strategies that can evade detection while maintaining attack functionality. We evaluated our approach across eight different IDS architectures, including RNN variants (RNN, LSTM, GRU) and Transformer-based models, using augmented datasets collected from two distinct vehicle environments (2016 Chevrolet Silverado and 2017 Subaru Forester). To enhance dataset diversity and address class imbalance, we applied data augmentation techniques including CaringCaribou-based attack generation and SMOTE-ENN hybrid sampling. Experimental results demonstrate remarkable attack effectiveness across different architectures and vehicle platforms. The DDQN agent achieved a perfect 100% evasion success rate against all RNN-variant IDS models when tested with fuzzing attacks on the training vehicle dataset, demonstrating strong transferability with an average 98.6% success rate on a different vehicle dataset. For DoS attacks, the agent exhibited variable performance with an overall average success rate of 49.32%, revealing dataset-specific vulnerabilities where success rates ranged from moderate performance on one vehicle dataset to near-perfect evasion on another. Notably, Transformer-based IDS demonstrated significantly greater robustness against both attack types compared to RNN variants, with success rates dropping to 66.77% for Fuzzing attacks on one dataset and complete resistance (0% success rate) on another. These findings highlight the importance of architectural diversity in building resilient IDS systems and underscore the persistent vulnerabilities of current deep learning approaches to sophisticated adversarial attacks. Our work contributes to the understanding of adversarial threats in automotive cybersecurity and emphasizes the need for adversarial-aware defense mechanisms in critical vehicle network infrastructures.

The Controller Area Network (CAN) is crucial for automotive safety, yet remains vulnerable to various fuzzing attacks that can compromise vehicle operations. This paper presents a comprehensive detection framework that identifies both common CAN vulnerabilities (DoS, Spoofing, Replay, and general Fuzzing) and specific fuzzer attack types (identity, replay, random, brute force, and mutation-based) using deep learning-based models. We evaluate four recurrent neural network architectures, including standard RNN, Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), and Gated Recurrent Unit (GRU), across three CAN datasets: the publicly available Hacking Car and OTIDS datasets, along with our proprietary Multi-FuzzerCAN dataset. To address the inherent class imbalance in attack data, we implement targeted random oversampling and random undersampling techniques tailored to each dataset’s distribution characteristics, significantly improving model performance. Our experimental results demonstrate that all four models achieve exceptional accuracy, recall, precision, and F1 scores across all datasets, with LSTM and BiLSTM architectures consistently outperforming other approaches. These findings establish the viability of combining deep learning models with data balancing techniques to enhance the resilience of automotive CAN networks against diverse cyber threats, especially multi-fuzzer attacks.

Text recognition on coffee bean package labels is of great importance for product tracking and brand verification, but it poses a challenge due to variations in image quality, packaging materials, and environmental conditions. In this paper, we propose a pipeline that combines several image enhancement techniques and is followed by an Optical Character Recognition (OCR) model based on vision–language (VL) Qwen VL variants, conditioned by structured prompts. To facilitate the evaluation, we construct a coffee bean package image set containing two subsets, namely low-resolution (LRCB) and high-resolution coffee bean image sets (HRCB), enclosing multiple real-world challenges. These cases involve various packaging types (bottles and bags), label sides (front and back), rotation, and different illumination. To address the image quality problem, we design a dedicated preprocessing pipeline for package label situations. We develop and evaluate four Qwen-VL OCR variants with prompt engineering, which are compared against four baselines: DocTR, PaddleOCR, EasyOCR, and Tesseract. Extensive comparison using various metrics, including the Levenshtein distance, Cosine similarity, Jaccard index, Exact Match, BLEU score, and ROUGE scores (ROUGE-1, ROUGE-2, and ROUGE-L), proves significant improvements upon the baselines. In addition, the public POIE dataset validation test proves how well the framework can generalize, thus demonstrating its practicality and reliability for label recognition.

The rapid proliferation of unmanned aerial vehicles (UAVs) has created an urgent need for robust detection & identification systems to ensure airspace security and safety. However, the scarcity of large-scale, diverse, and accurately annotated real-world datasets hinders the development of effective UAV detection & identification algorithms. To address this challenge, we present the RV-DroneEye (Realistic Virtual DroneEye) Dataset, a comprehensive framework for generating synthetic datasets utilizing the Unity 3D simulation engine to enhance UAV detection training. Additionally, we leverage photorealistic augmentation using Flux.1 diffusion-based model as a base, diverse environmental conditions, and physically accurate flight dynamics to generate large-scale annotated datasets that capture the visual complexity of real-world UAV detection scenarios. Then we evaluate our dataset’s generalization on various benchmarks and train multiple object-detection models. The RV-DroneEye dataset includes diverse UAV models, environments (urban, forest, lake), weather, and lighting conditions.We assess its effectiveness by training state-of-the-art object detection models and evaluating them on real-world test sets, including a multiclass task for more than 20 UAV types. Results show that models trained on RV-DroneEye achieve comparable or better UAV pattern generalization than those using limited real-world data, with marked gains in challenging scenarios such as low-light conditions, extreme angles, and cluttered backgrounds.