The growing complexity of service demands and user interactions in the Internet of Everything (IoE) necessitates intelligent systems that can adapt and comprehend human interactions. The interactions are interpreted through multiple modalities, including audio, text, and real-time observations, enabling personalized and accurate responses via Natural Language Processing (NLP) techniques. The existing approaches struggle to manage the uncertainty and computation delay while processing voice inputs. Therefore, this paper introduces Graph-Aided flow-based neural networks for NLP (GraphNetNLP) to effectively analyze and leverage user intent for intelligent social computing recommendations. The GraphNetNLP approach integrates the graph networks and natural language processing techniques that utilize voice and audio inputs to develop an interconnected cyclic graph that can be used to understand the demands and services provided to the user. In addition, recurrent graph mapping and training processes are utilized along with the certainty factors to analyze the disconnections. The certainty factors are selected based on the mapped and exhausted features of each iteration. The successful training process minimizes computational complexity by up to 8.86%, uncertainty by up to 6.87%, improves accuracy by up to 9.68%, and increases processing ratio by up to 11.77%. Thus, the introduced GraphNetNLP-based information processing is effectively utilized in text and other (IoE) applications.

The rapid development and deployment of Internet of Things (IoT) devices in modern networks and Industry 4.0 have attracted substantial interest from cybersecurity researchers. In this study, we propose a software-defined framework that improves network intrusion detection systems by using manufacturer usage description (MUD) to enhance the behavioral monitoring in IoT networks. We aim to explore whether Industrial IoT (IIoT) devices typically serve a common role in cyber–physical systems, and their communications exhibit predictable patterns that can be defined in MUD profile(s) formally and succinctly. We design a framework that utilizes the concept of digital twins and software-defined networking to improve the security of IIoT environments. The MUD data are profiled, and the actions are evaluated on the network digital twin before they are used in the physical network. The behavioral profiling system is updated in real time, thereby improving the overall system security and compliance to policies in the IoT deployment. Evaluation results show that our solution outperforms existing approaches substantially in terms of attack detection accuracy, predicting security incidents, response time, and resource usage.

To ensure the proper functioning and performance of Industrial grade Internet of Things devices (IIoT) in Industry 4.0 networks, it is critical to identify the capabilities and malfunctions of their component devices (e.g., sensors, actuators, and controllers) and detect potential misbehavior arising due to cyber-attacks, and misconfiguration. We envision future IoT devices embed behavioral profiles throughSecurity-by-Contract(S×C) that are easy to validate and verify against network security policies; manufacturers to provide manufacturer usage description (MUD) profiles as amanifestfor the devices to signal to the network what sort of access and network functionality they require to properly function. We design authentication in the IoT onboarding process, employ blockchains to a verifiable and immutable repository to store this network manifests, that is signed and verifiable with S×C basedsmart contractsby the device manufacturer, or industry authority. The integrated framework combines blockchains and S×C security contracts, MUD-based behavioral fingerprinting, and software-defined-networking for managing the security of IIoT ecosystems. Finally, the proposed scheme is validated in a simulated IoT environment on various performance parameters.

The technologies for real-time multimedia transmission and immersive 3D gaming applications are rapidly emerging, posing challenges in terms of performance, security, authentication, data privacy, and encoding. The communication channel for these multimedia applications must be secure and reliable from network attack vectors and data-contents must employ strong encryption to preserve privacy and confidentiality. Towards delivering secure multimedia application environment for 5G networks, we propose an SDN/NFV (Software-Defined-Networking/Network-Function-Virtualization) framework called STREK , which attempts to deliver highly adaptable Quality-of-Experience (QoE), Security, and Authentication functions for multi-domain Cloud to Edge networks. The STREK architecture consists of a holistic SDNFV dataplane, NFV service-chaining and network slicing, a lightweight adaptable hybrid cipher scheme called TREK, and an open RESTful API for applications to deploy custom policies at runtime for multimedia services. For multi-domain/small-cell deployments, the key-generation scheme is dynamic at flow/session-level, and the handover authentication scheme uses a novel method to exchange security credentials with the Access Points (APs) of neighborhood cells. This scheme is designed to improve authentication function during handover with low overhead, delivering the 5G ultra-low latency requirements. We present the experiments with both software and hardware-based implementations and compare our solution with popular lightweight cryptographic solutions, standard open source software, and SDN-based research proposals for 5G multimedia. In the microbenchmarks, STREK achieves smaller hardware, low overhead, low computation, higher attack resistance, and offers better network performance for multimedia streaming applications. In real-time multimedia use-cases, STREK shows greater level of quality distortion for multimedia contents with minimal encryption bitrate overhead to deliver data confidentiality, immunity to common cryptanalysis, and significant resistance to communication channel attacks, in the context of low-latency 5G networks.