RESUMO
Deep learning algorithms have a wide range of applications, including cancer diagnosis, face and speech recognition, object recognition, etc. It is critical to protect these models since any changes to them can result in serious losses in a variety of ways. This article proposes the consortium blockchain-enabled conventional neural network (CBCNN), a four-layered paradigm for detecting malicious vehicles. Layer-1 is a convolutional neural network-enabled Internet-of-Things (IoT) model for the vehicle; Layer-2 is a spatial pyramid polling layer for the vehicle; Layer-3 is a fully connected layer for the vehicle; and Layer-4 is a consortium blockchain for the vehicle. The first three layers accurately identify the vehicles, while the final layer prevents any malicious attempts. The primary goal of the four-layered paradigm is to successfully identify malicious vehicles and mitigate the potential risks they pose using multi-label classification. Furthermore, the proposed CBCNN approach is employed to ensure tamper-proof protection against a parameter manipulation attack. The consortium blockchain employs a proof-of-luck mechanism, allowing vehicles to save energy while delivering accurate information about the vehicle's nature to the "vehicle management system." C++ coding is employed to implement the approach, and the ns-3.34 platform is used for simulation. The ns3-ai module is specifically utilized to detect anomalies in the Internet of Vehicles (IoVs). Finally, a comparative analysis is conducted between the proposed CBCNN approach and state-of-the-art methods. The results confirm that the proposed CBCNN approach outperforms competing methods in terms of malicious label detection, average accuracy, loss ratio, and cost reduction.
RESUMO
Low-speed internet can negatively impact incident response by causing delayed detection, ineffective response, poor collaboration, inaccurate analysis, and increased risk. Slow internet speeds can delay the receipt and analysis of data, making it difficult for security teams to access the relevant information and take action, leading to a fragmented and inadequate response. All of these factors can increase the risk of data breaches and other security incidents and their impact on IoT-enabled communication. This study combines virtual network function (VNF) technology with software -defined networking (SDN) called virtual network function software-defined networking (VNFSDN). The adoption of the VNFSDN approach has the potential to enhance network security and efficiency while reducing the risk of cyberattacks. This approach supports IoT devices that can analyze large volumes of data in real time. The proposed VNFSDN can dynamically adapt to changing security requirements and network conditions for IoT devices. VNFSDN uses threat filtration and threat-capturing and decision-driven algorithms to minimize cyber risks for IoT devices and enhance network performance. Additionally, the integrity of IoT devices is safeguarded by addressing the three risk categories of data manipulation, insertion, and deletion. Furthermore, the prioritized delegated proof of stake (PDPoS) consensus variant is integrated with VNFSDN to combat attacks. This variant addresses the scalability issue of blockchain technology by providing a safe and adaptable environment for IoT devices that can quickly be scaled up and down to pull together the changing demands of the organization, allowing IoT devices to efficiently utilize resources. The PDPoS variant provides flexibility to IoT devices to proactively respond to potential security threats, preventing or mitigating the impact of cyberattacks. The proposed VNFSDN dynamically adapts to the changing security requirements and network conditions, improving network resiliency and enabling proactive threat detection. Finally, we compare the proposed VNFSDN to existing state-of-the-art approaches. According to the results, the proposed VNFSDN has a 0.08 ms minimum response time, a 2% packet loss rate, 99.5% network availability, a 99.36% threat detection rate, and a 99.77% detection accuracy with 1% malicious nodes.