This research introduces a comprehensive collaborative intrusion detection system (CIDS) framework aimed at bolstering the security of Internet of Things (IoT) environments by synergistically integrating lightweight architecture, trust management, and privacy-preserving mechanisms. The proposed hierarchical architecture spans edge, fog, and cloud layers, ensuring efficient and scalable collaborative intrusion detection. Trustworthiness is established through the incorporation of distributed ledger technology (DLT), leveraging blockchain frameworks to enhance the reliability and transparency of communication among IoT devices. Furthermore, the research adopts federated learning (FL) techniques to address privacy concerns, allowing devices to collaboratively learn from decentralized data sources while preserving individual data privacy. Validation of the proposed approach is conducted using the CICIoT2023 dataset, demonstrating its effectiveness in enhancing the security posture of IoT ecosystems. This research contributes to the advancement of secure and resilient IoT infrastructures, addressing the imperative need for lightweight, trust-managing, and privacy-preserving solutions in the face of evolving cybersecurity challenges. According to our experiments, the proposed model achieved an average accuracy of 97.65%, precision of 97.65%, recall of 100%, and F1-score of 98.81% when detecting various attacks on IoT systems with heterogeneous devices and networks. The system is a lightweight system when compared with traditional intrusion detection that uses centralized learning in terms of network latency and memory consumption. The proposed system shows trust and can keep private data in an IoT environment.

This review article looks at recent research on Federated Learning (FL) for Collaborative Intrusion Detection Systems (CIDS) to establish a taxonomy and survey. The motivation behind this review comes from the difficulty of detecting coordinated cyberattacks in large-scale distributed networks. Collaborative anomalies are one of the network anomalies that need to be detected through robust collaborative learning methods. FL is promising collaborative learning method in recent research. This review aims to offer insights and lesson learn for creating a taxonomy of collaborative anomaly detection in CIDS using FL as a collaborative learning method. Our findings suggest that a taxonomy is required to map the discussion area, including an algorithm for training the learning model, the dataset, global aggregation model, system architecture, security, and privacy. Our results indicate that FL is a promising approach for collaborative anomaly detection in CIDS, and the proposed taxonomy could be useful for future research in this area. Overall, this review contributes to the growing knowledge of FL for CIDS, providing insights and lessons for researchers and practitioners. This research also concludes significant challenges, opportunities, and future directions in CIDS based on collaborative anomaly detection using FL.

Ethereum is one of the oldest examples of blockchain technology provides a system that converts centralized storage to distributed and records transactions by way of decentralized and not by a centralized system and can be verified by each node, therefore it is suitable for storing fingerprints from official diploma documents and transcripts that are published. Smart contract is needed for making contract transactions to Ethereum with programming code, so contracts such as diplomas and transcripts uploaded on the Ethereum blockchain can distribute and produce diploma validation and the authenticity of transcripts with transaction hash, consensus, and comply with ERC-721 token standardization. The results showed that a sample of 5 electronic documents in pdf format with a transaction speed of 1 second on each file that were published and secured with Ethereum blockchain technology can be easily verified for authenticity, the system proposed and developed by us takes in consideration invalid and failure cases by giving the necessary feedback to the user.

Detecting coordinated attacks in cybersecurity is challenging due to their sophisticated and distributed nature, making traditional Intrusion Detection Systems often ineffective, especially in heterogeneous networks with diverse devices and systems. This research introduces a novel Collaborative Intrusion Detection System (CIDS) using a Weighted Ensemble Averaging Deep Neural Network (WEA-DNN) designed to detect such attacks. The WEA-DNN combines deep learning techniques and ensemble methods to enhance detection capabilities by integrating multiple Deep Neural Network (DNN) models, each trained on different data subsets with varying architectures. Differential Evolution optimizes the model’s contributions by calculating optimal weights, allowing the system to collaboratively analyze network traffic data from diverse sources. Extensive experiments on real-world datasets like CICIDS2017, CSE-CICIDS2018, CICToNIoT, and CICBotIoT show that the CIDS framework achieves an average accuracy of 93.8%, precision of 78.6%, recall of 60.4%, and an F1-score of 62.4%, surpassing traditional ensemble models and matching the performance of local DNN models. This demonstrates the practical benefits of WEA-DNN in improving detection capabilities in real-world heterogeneous network environments, offering superior adaptability and robustness in handling complex attack patterns.

This research introduces a pioneering approach, termed Hierarchical Collaborative Botnet Detection, leveraging Federated Deep Learning to address the escalating security concerns within the Internet of Things (IoT) ecosystems characterized by heterogeneous devices. The proposed framework establishes a hierarchical structure facilitating efficient collaboration among devices at different levels, enabling scalable and distributed botnet detection. Federated Deep Learning ensures model training without centralizing sensitive data, respecting privacy constraints inherent in IoT environments. The methodology involves the development of a collaborative learning model capable of analyzing diverse data sources across the IoT landscape, utilizing the N-BaIoT dataset for comprehensive evaluation. Comprehensive simulations and experiments, conducted with the N-BaIoT dataset, showcase the robustness and efficiency of the proposed approach in detecting botnet activities across diverse IoT devices. Based on experimental results, the proposed method can identify botnets with an average accuracy of 98,97, precision of 98,75, recall of 99,41, and an F1-score of 99,11. The hierarchical and federated nature of the model contributes to a more resilient and scalable botnet detection system for large-scale IoT deployments, laying the foundation for a secure and collaborative IoT landscape in the face of evolving cyber threats.

The development of the Internet of Things (IoT) can be found in various places. However, multiple kinds of attacks have also increased. IoT devices are very vulnerable to attacks, both physical and non-physical, because of their unmanned nature. In non-physical attacks, the most important thing is to secure the data on memory devices. Physical unclonable function (PUF) is the strongest and lightest method to securing memory devices and can be used on unmanned IoT devices. The advantage of PUF over current classical cryptography types is its compatibility on IoT devices with limited computing resources. However, before PUF can be claimed to provide security property, it must meet the evaluation indicators: randomness, uniqueness, and steadiness. PUF can be the best solution for securing data on IoT devices because the encryption process does not put a secret key on the device. Instead, the key is generated randomly. This research is evaluating two different PUF chips with the same PUF design. We designed the arbiter PUF on the FPGA and evaluated the results of the responses given. Through rigorous experiments, this research succeeded to evaluate the three indicators of PUF where the randomness is 54.43%:45.4%, and 25.88%: 74.2%, the uniqueness between chip is 69.53%, and lastly, the steadiness is 89.84%, and 91.41%.