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 Internet of Things (IoT) has been instrumental in bringing about several advancements and innovations in the domain of healthcare. Healthcare professionals are essentially life savers when it comes to handling emergency cases, such as accidents, heart attacks, etc. Only the patient’s vital parameters generally characterize emergency cases, and the doctors must wait for additional details for a wholesome diagnosis. As a result, the treatment processes and procedures sometimes get hastened and, in turn, put the patients’ lives at risk. It would always be helpful for doctors to be equipped with the medical requirements in advance for deciding the right course of action, thereby increasing the scope and chances of recovery. In this work, multimodel IoT (MMIoT) devices are deployed to monitor and collect health data from different body parts simultaneously. The healthcare data comprises signals and imagery captured from the MMIoT devices. Both the U-Net model and LSTM model are used to analyze the data automatically. The data processing is carried out by the server connected to the MMIoT network. All the medical IoT devices experimented with in this work are interconnected using a potential 5G network for optimal data transmission. The output obtained from the U-Net and the LSTM are channelized through a dense layer to classify the health anomalies accurately. It would not only facilitate but also educate medical professionals to handle unseen and typical cases in the future confidently. It can improve the overall quality of treatment and save lives with the best available resources.

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.

Summary Currently, core networking architectures are facing disruptive developments, due to emergence of paradigms such as Software‐Defined‐Networking (SDN) for control, Network Function Virtualization (NFV) for services, and so on. These are the key enabling technologies for future applications in 5G and locality‐based Internet of things (IoT)/wireless sensor network services. The proliferation of IoT devices at the Edge networks is driving the growth of all‐connected world of Internet traffic. In the Cloud‐to‐Things continuum, processing of information and data at the Edge mandates development of security best practices to arise within a fog computing environment. Service providers are transforming their business using NFV‐based services and SDN‐enabled networks. The SDN paradigm offers an easily programmable model, global view, and control for modern networks, which demand faster response to security incidents and dynamically enforce countermeasures to intrusions and cyberattacks. This article proposes an autonomic multilayer security framework called Distributed Threat Analytics and Response System (DTARS) for a converged architecture of Fog/Edge computing and SDN infrastructures, for emerging applications in IoT and 5G networks. The major detection scheme is deployed within the data plane, consisting of a coarse‐grained behavioral, anti‐spoofing, flow monitoring and fine‐grained traffic multi‐feature entropy‐based algorithms. We developed exemplary defense applications under DTARS framework, on a malware testbed imitating the real‐life DDoS/botnets such as Mirai. The experiments and analysis show that DTARS is capable of detecting attacks in real‐time with accuracy more than 95% under attack intensities up to 50 000 packets/s. The benign traffic forwarding rate remains unaffected with DTARS, while it drops down to 65% with traditional NIDS for advanced DDoS attacks. Further, DTARS achieves this performance without incurring additional latency due to data plane overhead.