12 December 2023 in IEEE Transactions on Consumer Electronics
The profound era of cloud computing (CC) is revolutionizing Industry 5.0in which users have online access to network services including better, transparent user management and the capacity to gather and analyze data. The services of the cloud paradigm have been adopted by academia, industries, healthcare, smart homes, and other areas due to cost-efficient and on-demand resources for IoT applications, but security and privacy of patient data is a major issue with cloud paradigm. For intrusion detection systems (IDS), adversarial machine learning (AML) has been promising to secure individual IoT devices from various modern threats. Network traffic anomalies brought on by both well-known assaults and recently discovered attacks are typically detected by adversarial machine learning-based intrusion detection systems (AML-IDS) in real time. This research proposes a novel technique in cloud security enhancement based on consumer IoT utilizing AML techniques in smart healthcare. The security of cloud networks is enhanced using trust-based encryption cryptographic analysis. The healthcare data is analyzed using structure-based Markov sparse Bayesian neural networks in smart healthcare. The experimental results are improved up to 9% in terms of data transmission ratio, specificity, training accuracy, validation accuracy, and security analysis.
1 January 2016 in International Journal of Sensor Networks
The speedy raising insalubrious environment, where peoples have less focus towards own health and physical fitness has impel the need of caregivers and doctors. In addition, increase in elderly population and numerous chronic diseases fortify the need of real-time healthcare system to monitor numerous physiological sign at their doorstep. The advances in sensing, computing and communication technologies coupled with level of comfort, cost reduction, and continuously health monitoring have led to the development of wireless body area networks (WBANs). Development of WBANs impels to make use of wearable and implanted sensor devices for various physiological sign monitoring. Furthermore, it provides long term, real-time healthcare monitoring to individual personal without restricting their daily life activities. In this paper, we proposed a general real-time healthcare monitoring system architecture. We also summarised the need, challenges and radio technologies of WBANs, since it is the key factor to achieve low power and low latency.
28 October 2026 in ACM Transactions on Multimedia Computing, Communications, and Applications
The Internet of Medical Things (IoMT) generates distributed multimodal health data that support multimodal large language models (MLLMs) for diagnosis, risk prediction, and clinical decision support. Trustworthy healthcare inference requires fine-grained control over modality access under task-specific authorization and privacy constraints. We propose a modality-aware trustworthy data access framework that independently authorizes requested modalities and enforces task-specific access policies. By integrating BBS+ signatures, zero-knowledge proofs, and authenticated key agreement, the framework supports selective disclosure of certified requester attributes while protecting unrelated information and long-term identity. Credential presentations are bound to the requested modality, healthcare task, revocation state, and accountability context, enabling auditable access decisions. Security analysis establishes modality authorization, mutual authentication, session-key security, selective-disclosure privacy, revocation enforcement, and controlled accountability. Evaluation on the OpenI chest X-ray dataset with MedGemma demonstrates how authorized modality availability influences downstream inference, with joint image–text input outperforming image-only inference. The framework further achieves millisecond-level local cryptographic processing under a constrained gateway profile and supports authorization over IEEE 802.15.4/6LoWPAN with scalable revocation synchronization. These results demonstrate the feasibility of privacy-preserving modality access governance for multimodal healthcare inference.