Internet of Things (IoT) devices are leading to advancements in innovation, efficiency, and sustainability across various industries. However, as the number of connected IoT devices increases, the risk of intrusion becomes a major concern in IoT security. To prevent intrusions, it is crucial to implement intrusion detection systems (IDSs) that can detect and prevent such attacks. IDSs are a critical component of cybersecurity infrastructure. They are designed to detect and respond to malicious activities within a network or system. Traditional IDS methods rely on predefined signatures or rules to identify known threats, but these techniques may struggle to detect novel or sophisticated attacks. The implementation of IDSs with machine learning (ML) and deep learning (DL) techniques has been proposed to improve IDSs’ ability to detect attacks. This will enhance overall cybersecurity posture and resilience. However, ML and DL techniques face several issues that may impact the models’ performance and effectiveness, such as overfitting and the effects of unimportant features on finding meaningful patterns. To ensure better performance and reliability of machine learning models in IDSs when dealing with new and unseen threats, the models need to be optimized. This can be done by addressing overfitting and implementing feature selection. In this paper, we propose a scheme to optimize IoT intrusion detection by using class balancing and feature selection for preprocessing. We evaluated the experiment on the UNSW-NB15 dataset and the NSL-KD dataset by implementing two different ensemble models: one using a support vector machine (SVM) with bagging and another using long short-term memory (LSTM) with stacking. The results of the performance and the confusion matrix show that the LSTM stacking with analysis of variance (ANOVA) feature selection model is a superior model for classifying network attacks. It has remarkable accuracies of $96.92\%$ and $99.77\%$ and overfitting values of $0.33\%$ and $0.04\%$ on the two datasets, respectively. The model’s ROC is also shaped with a sharp bend, with AUC values of $0.9665$ and $0.9971$ for the UNSW-NB15 dataset and the NSL-KD dataset, respectively.

The rapid growth of Internet of Things (IoT) networks has increased security risks, making it essential to have effective Intrusion Detection Systems (IDS) for real-time threat detection. Deep learning techniques offer promising solutions for such detection due to their superior complex pattern recognition and anomaly detection capabilities in large datasets. This paper proposes an optimized ensemble-based IDS designed specifically for efficient deployment on edge hardware. However, deploying such computationally intensive models on resource-limited edge devices remains a significant challenge due to model size and computational overhead on devices with limited processing capabilities. Building upon our previously developed stacked Long Short-Term Memory (LSTM) model integrated with ANOVA feature selection, we optimize it by integrating dual-stage model compression: pruning and quantization to create a lightweight model suitable for real-time inference on Raspberry Pi devices. To evaluate the system under realistic conditions, we combined with a Kafka-based testbed to simulate dynamic IoT environments with variable traffic loads, delays, and multiple simultaneous attack sources. This enables the assessment of detection performance under varying traffic volumes, latency, and overlapping attack scenarios. The proposed system maintains high detection performance with accuracy of 97.3% across all test scenarios, while efficiently leveraging multi-core processing with peak CPU usage reaching 111.8%. These results demonstrate the system’s practical viability for real-time IoT security at the edge.

Ensuring the reliability of data gathering from every connected device is an essential issue for promoting the advancement of the next paradigm shift, i.e., Industry 4.0. Blockchain technology is becoming recognized as an advanced tool. However, data collaboration using blockchain has not progressed sufficiently among companies in the industrial supply chain (SC) that handle sensitive data, such as those related to product quality, etc. There are two reasons why data utilization is not sufficiently advanced in the industrial SC. The first is that manufacturing information is top secret. Blockchain mechanisms, such as Bitcoin, which uses PKI, require plaintext to be shared between companies to verify the identity of the company that sent the data. Another is that the merits of data collaboration between companies have not been materialized. To solve these problems, this paper proposes a business-to-business collaboration system using homomorphic encryption and blockchain techniques. Using the proposed system, each company can exchange encrypted confidential information and utilize the data for its own business. In a trial, an equipment manufacturer was able to identify the quality change caused by a decrease in equipment performance as a cryptographic value from blockchain and to identify the change one month earlier without knowing the quality value.

A cloud service to offer entropy has been paid much attention to. As one of the entropy sources, a physical random number generator is used as a true random number generator, relying on its irreproducibility. This paper focuses on a physical random number generator using a field-programmable gate array as an entropy source by employing ring oscillator circuits as a representative true random number generator. This paper investigates the effects of an XOR gate in the oscillation circuit by observing the output signal period. It aims to reveal the relationship between inputs and the output through the XOR gate in the target generator. The authors conduct two experiments to consider the relevance. It is confirmed that combining two ring oscillators with an XOR gate increases the complexity of the output cycle. In addition, verification using state transitions showed that the probability of the state transitions was evenly distributed by increasing the number of ring oscillator circuits.

Vehicular Ad-Hoc Networks (VANETs) play an essential role in the intelligent transportation era, furnishing users with essential roadway data to facilitate optimal route selection and mitigate the risk of accidents. However, the network exposure makes VANETs susceptible to cyber threats, making authentication crucial for ensuring security and integrity. Therefore, joining entity verification is essential to ensure the integrity and security of communication in VANETs. However, to authenticate the entities, authentication time should be minimized to guarantee fast and secure authentication procedures. We propose an authentication system for VANETs using blockchain and Kerberos for storing authentication messages in a blockchain ledger accessible to Trusted Authentication Servers (TASs) and Roadside Units (RSUs). We evaluate the system in three diverse network scenarios: suburban, urban with 1 TAS, and urban with 2 TASs. The findings reveal that this proposal is applicable in diverse network scenarios to fulfill the network requirements, including authentication, handover, and end-to-end delay, considering an additional TAS for an increasing number of vehicles. The system is also practicable in storing the authentication message in blockchain considering the gas values and memory size for all scenarios.