Network forensics is commonly used to identify and analyse evidence of any illegal or unauthorised activity in a given network. The collected information can be used for preventive measures against potential cyber attacks and serve as evidence acceptable in legal proceedings. Several conventional tools and techniques are available to identify and collect such pieces of evidence; however, most of them require expensive commercial resources, longer investigation times, and costly human expertise. Due to modern networks’ diverse and heterogeneous nature, forensic operations through conventional means become a cumbersome and challenging process. This calls for a new look at how network forensics is approached, considering contemporary approaches to network analysis. In this work, we explore artificial intelligence (AI) techniques based on contemporary machine learning (ML) algorithms such as deep learning (DL) to conduct network forensics. We also propose an investigation model based on AI/ML techniques that can analyse network traffic and behavioural patterns to identify any prior or potential cyber attacks. The proposed AI-based network forensics model speeds up the investigation process, boosting network monitoring without human intervention. This also aims to provide timely and accurate information to network administrators for quick and effective decisions, enabling them to avoid and circumvent future cyber attacks.

The integration of large language models (LLM) with multimodal agentic artificial intelligence (AI) within the medical Internet of Things (MIoT) ecosystem is redefining modern healthcare intelligence. This convergence enables continuous patient observation, adaptive clinical decision-making, and context-aware interaction between humans and machines across various biomedical data modalities. Healthcare systems generate a wide range of multimodal data, including textual records such as EHRs, prescriptions, and pathology notes; medical imagery such as CT, MRI, fundus, and radiographs; spoken data from consultations and transcriptions; video streams for rehabilitation and physiotherapy monitoring; and sensor readings such as ECG, SpO \({}_{2}\) , and glucose levels. Conventional unimodal algorithms fall short in interpreting this diversity, whereas LLM-augmented agentic frameworks fuse and reason over these heterogeneous sources, grounding their outputs in medical ontologies and coordinating task-specific agents to enhance real-world clinical workflows. This paper presents a comprehensive overview of multimodal agentic AI powered by LLM for MIoT-enabled healthcare systems. Introduces a six-dimensional unified taxonomy that covers multimodal input channels, fusion mechanisms, core LLM reasoning capabilities, agentic coordination models, computational deployment layers, and ethical governance frameworks. To contextualize this taxonomy, the discussion includes a Virtual Hospital case study centered on cancer that demonstrates how multimodal signals such as imaging, genomics, patient dialogues, and clinical updates integrate through intelligent agents to enable personalized diagnosis, automated documentation, home rehabilitation, and rapid intervention in emergencies. The survey also consolidates current progress on datasets, benchmarks, and evaluation protocols for AI in multimodal and agentic healthcare. The survey identifies critical research gaps, such as the lack of longitudinal multimodal datasets, standardized evaluation frameworks for multi-agent reasoning, and reliable methods to assess trustworthiness in clinical AI. Furthermore, it examines security and compliance issues such as adversarial manipulation, data leakage, and accountability across distributed agent networks, and it proposes countermeasures through federated data governance, secure MCP-oriented orchestration, and privacy-aware edge deployment strategies. By situating recent advances within the Virtual Hospital paradigm and oncology workflows, this study provides a systematic foundation for developing scalable, secure, and ethically aligned multimodal agentic systems based on LLMs, guiding the next generation of intelligent MIoT-driven healthcare ecosystems

The rapid expansion of wireless communication and the Internet of Everything (IoE) has transformed modern technology, necessitating secure and efficient Resource Allocation (RA) to optimize system performance. However, the increasing number of IoE devices introduces security vulnerabilities, particularly from Non-Legitimate Devices (NLDs) that threaten network integrity, data confidentiality, and system availability. This study proposes an RA model based on cyber threat intelligence (CTI) to detect and mitigate malicious devices, integrating a two-state Hidden Markov Model (HMM) for NLD identification and encryption/decryption mechanisms for secure task communication. The model is designed for IoE-Edge fog-based networks, reducing dependency on external cloud servers while leveraging 6G-enabled device clustering for optimized task distribution. A novel CTI-based RA mechanism, namely the Secure-Intelligent Main Task Off-loading Scheduling Algorithm (Sec- i MTOSA), is introduced to enhance intelligent scheduling and secure RA. Experimental results demonstrate that Sec- i MTOSA achieves an average of 93.7% accuracy in detecting NLDs while maintaining a secure RA process with only an average of 7.2% increase in end-to-end delay compared to non-secure traditional methods. These results validate the effectiveness of the model, demonstrating a high accuracy rate in identifying legitimate NLDs while maintaining a low computational overhead suitable for lightweight IoE-Edge environments. Although Sec- i MTOSA introduces minor end-to-end delays due to its embedded security features, it remains efficient for real-time IoE-Edge deployments. These findings establish CTI-driven RA as a scalable and secure approach for next-generation IoE-Edge networks.