Currently, cybersecurity is a topic of great importance for society. With the increase in the use of technology and the digitization of many activities, the number of cyber threats to which individuals and organizations are exposed has increased. In addition, the COVID-19 pandemic has accelerated the digitization of many processes, further increasing the risk of cyberattacks. One of the main causes of these problems is the lack of cyber security awareness, as many people and organizations do not have a proper understanding of cyber threats and the measures, they must take to protect themselves. As a solution to the lack of cybersecurity knowledge, this work proposes the development of a Capture the Flag platform for learning about cybersecurity. The objective is to provide a tool that allows the education of future professionals in this field and covers the existing demand for this type of specialist. The platform is made up of two sections, one for learning and the other for CTF. The first section allows teachers to contribute to the teaching of their students using challenges. The second section allows one to carry out competitions with effective results when acquiring knowledge and experience. The platform is evaluated using questionnaires and surveys to measure whether the platform fulfills its purpose.

The perishability of food products in the supply chain poses a significant challenge in ensuring quality and safety. Inefficient monitoring of temperature, humidity, and storage time results in substantial economic losses and increased health risks. Traditional traceability systems rely on manual audits or essential IoT platforms that lack predictive capabilities, leading to delayed anomaly detection and inefficient intervention. Blockchain-based solutions improve transparency but primarily focus on record verification rather than active anomaly detection and automated decision-making. This study proposes an integrated system combining Artificial Intelligence (AI), the Internet of Things (IoT), and blockchain to optimize food traceability through real-time monitoring, predictive analytics, and secure decentralized record management. The system deploys smart sensors across storage and transportation units to continuously collect environmental data, which is processed by a deep learning model trained to detect deviations with 92.4 % accuracy. Detected anomalies trigger automated responses via smart contracts in a blockchain network, ensuring immediate corrective actions while maintaining immutable audit records. Results demonstrate a 64.3 % reduction in response time, improving reaction efficiency to critical storage failures. Additionally, false positive alerts decreased by 73.1 %, optimizing operational efficiency and minimizing unnecessary interventions. The blockchain implementation reduced storage overhead by 76.9%, ensuring scalability and long-term feasibility. This research establishes a foundation for intelligent, automated food supply chain management, demonstrating that integrating AI, IoT, and blockchain enhances safety, reduces waste, and optimizes logistics. Future work will focus on improvements in large-scale deployment and computational efficiency to refine this innovative approach.

This study aims to optimize blockchain consensus mechanisms by integrating artificial intelligence techniques to address critical limitations in latency, scalability, computational efficiency, and security inherent in traditional protocols, such as PoW, PoS, and PBFT. The proposed model combines deep neural networks (DNNs) for feature extraction with deep reinforcement learning (DRL), specifically Deep Q-Networks (DQN) and Proximal Policy Optimization (PPO), to enable dynamic validator selection and real-time adjustment of consensus difficulty. The training process utilizes a hybrid dataset of historical blockchain records from Ethereum and Hyperledger networks and synthetic data from simulated attack scenarios involving Sybil, 51%, and DoS threats. Experimental evaluations were conducted in private and permitted environments under varying transactional loads. Results show a 60% reduction in confirmation latency compared to PoW, achieving 320 ms, and a 20% improvement over PBFT. Transaction throughput increased to 22,000 transactions per second (TPS), and computational resource consumption was reduced by 30%. The model achieved an attack tolerance of up to 92%, significantly enhancing network resilience. The novelty of this work lies in its autonomous consensus optimization strategy, which enables adaptive and secure protocol behaviour without manual intervention, representing a scalable and efficient solution for future blockchain infrastructures.

The journal retracts the article, Development of a Platform for Learning Cybersecurity Using Capturing the Flag Competitions

Automating mathematical proficiency assessment remains challenging due to the lack of adaptive, psychometrically consistent mechanisms in both traditional and machine-learning approaches. Rule-based and supervised models evaluate performance without modeling conceptual dependencies or accounting for varying difficulty across curricula. This study introduces an adaptive assessment framework that integrates Graph Neural Networks (GNNs) and Deep Q-Networks (DQNs) to infer mathematical proficiency and dynamically optimize question selection. The GNN captures structural relations between mathematical concepts, while the reinforcement learning agent adjusts the difficulty trajectory in real time. A hybrid calibration process inspired by Item Response Theory ensures that difficulty levels are comparable across heterogeneous datasets. Experimental results show that the model achieves high sensitivity, with recall between 85 and 90% and F1-scores up to 90.8%, outperforming DNN and logistic regression baselines. These results highlight the system’s capacity to detect learning difficulties, maintain scalability under high concurrency, and provide pedagogically meaningful feedback. The integration of graph-based knowledge representation, reinforcement learning, and psychometric calibration establishes a robust foundation for scalable, explainable, and adaptive assessment, particularly within mathematics and other domains characterized by well-defined conceptual structures.