The exponential growth of sensitive patient information and diagnostic records in digital healthcare systems has increased the complexity of data protection, while frequent medical data breaches severely compromise system security and reliability. Existing privacy protection techniques often lack robustness and real-time capabilities in high-noise, high-packet-loss, and dynamic network environments, limiting their effectiveness in detecting healthcare data leaks. To address these challenges, we propose a Swarm Intelligence-Based Network Watermarking (SIBW) method for real-time privacy data leakage detection in digital healthcare systems. SIBW integrates fountain codes with outer error correction codes and employs a Multi-Phase Synergistic Swarm Optimization Algorithm (MPSSOA) to dynamically optimize encoding parameters, significantly enhancing the robustness and interference resistance of watermark detection. Additionally, a reliable synchronization sequence and lightweight embedding mechanism are designed to ensure adaptability to complex, dynamic networks. Experimental results demonstrate that SIBW achieves over 90% detection accuracy under high latency jitter and packet loss conditions, surpassing existing methods in both robustness and efficiency. With a compact design of only 3.7 MB, SIBW is particularly suited for rapid deployment in resource-constrained digital healthcare systems.

With the rapid expansion of the Internet of Medical Things (IoMT) and cloud computing, ensuring secure communication in e-health systems has become increasingly critical. However, many existing authentication solutions suffer from excessive overhead and security vulnerabilities. To address these challenges, we present a lightweight, high-speed authentication protocol that relies on secure hash functions and XOR operations, facilitating efficient mutual authentication among users, trusted servers, and medical servers while establishing session keys for data exchange. We then rigorously assess our protocol's security against a comprehensive threat model, employing both informal methods and formal analyses, including Real-Or-Random (ROR) model, BAN logic, and automated verification via ProVerif. The results demonstrate that our protocol remains resilient against known attacks and satisfies e-health security standards. Furthermore, a detailed performance comparison reveals that our approach significantly reduces some costs compared to existing schemes, while reinforcing security and privacy protections.

The real-time processing of large-scale, heterogeneous tasks—including CPU-only, general-purpose GPU, and specialized GPU tasks—poses significant challenges in Internet of Things (IoT) systems, driven by severe GPU resource fragmentation, inefficient CPU and memory resource utilization on edge servers. These issues often compromise system processing performance and server stability. To address these issues, we formulate a multi-stage mixed-integer nonlinear programming (MINLP) model, to jointly optimize GPU fragmentation rate and system processing capability. We then introduce a novel deviation-based Lyapunov optimization framework that explicitly maintains memory utilization around a predefined optimal threshold, effectively balancing resource usage and system stability. Finally, to achieve real-time decision-making for massive tasks in dynamic systems with randomly arriving tasks, we propose the MA-LHTO algorithm, a multi-agent deep reinforcement learning approach that incorporates a multi-head architecture, entropy-based exploration, and a parameter reset mechanism. Experimental results confirm that our algorithm significantly improves resource utilization, and exhibits good performance under various working conditions.

In dynamic Internet of low-altitude UAVs (IoLoUA) systems, the task generation frequency and resource demand are highly uncertain, complicating the real-time formulation of efficient task-processing strategies and resulting in task backlogs, computational bottlenecks, and GPU fragmentation. To address these challenges, we propose a UAV-assisted computation reuse scheme, wherein UAVs cache the results of reusable tasks, i.e., their outputs can be utilized by other tasks within a defined time window, thereby reducing redundant computations and alleviating server load. Additionally, to jointly optimize massive task offloading and GPU resource fragmentation, we model the problem as a multi-stage mixed-integer nonlinear programming (MINLP) problem. To effectively solve this problem, we introduce the Double-time-scale decision algorithm (Double-TSD), which integrates short-term task processing decisions driven by reinforcement learning with long-term caching decisions based on temporal deep learning, efficiently handles large-scale tasks while minimizing GPU fragmentation. Experimental results show that the proposed method consistently achieves better performance than state-of-the-art approaches such as BLEAQ-II, SCRACO, LRMA, and DGL-DDPG, particularly in reducing GPU resource fragmentation and enhancing system efficiency.

Due to the proliferation of IoT devices, electronic health records, and clinical imaging systems, medical data volumes have increased dramatically. This clearly exposes the weaknesses of traditional healthcare infrastructures: limited network bandwidth, limited computational resources, and scaling bottlenecks. This paper proposes a multi-layered architecture named HOBNET (Healthcare Optimized Blockchain Network Protocol Stack) that optimizes bandwidth, resource utilization, and storage during healthcare data management. HOBNET consists of four protocols: the Transaction Batching Protocol (TBP), which exploits bandwidth-efficient semantic aggregation; the By-pass Chain Management Protocol (BCMP), which utilizes storage-efficient dual-chain separation with AES-256-GCM payload encryption and hash-commitment-based integrity verification; the Lightweight Verification Protocol (LVP), which allows resource-constrained end-devices to perform fixed-cost hash-chain-based proof verification with O(log4n) Quad-Merkle trees; and the Epidemic Broadcasting Protocol (EBP), which enables adaptive, bandwidth-aware data diffusion tolerating f < n/3 Byzantine nodes. HOBNET assumes a semi-trusted adversary model where a certain fraction (up to 30%) of the nodes is allowed to be Byzantine. The Byzantine nodes include compromised gateways. There is also a set of colluding storage nodes. These Conspiring storage nodes are modeled as honest-but-curious. The simulation results reveal that HOBNET achieves a 13–42× higher throughput, 4–7× lower latency, and 84.6% savings in storage as compared to Hyperledger Fabric and MedBloc. Proposed stack enables the support of 250+ resource-constrained IoT devices with 99.1% delivery reliability under 30% node failure. HOBNET also provides a jurisdiction-aware routing mechanism designed to support HIPAA/GDPR data residency requirements.

In IoLoUA systems, task arrivals are asynchronous and resource demands are heterogeneous. However, these characteristics cause newly arriving tasks to compete with unfinished ones for limited resources across time slots, leading to cross-slot contention and rapid system-state fluctuations. Such non-stationarity makes it difficult to maintain accurate state awareness, thereby reducing the feasibility of offloading decisions. To address this challenge, we propose Hierarchical Collaborative Asynchronous Offloading (HCAO), an integrated framework that combines scheduling, state modeling, and decision-making for efficient task processing in dynamic environments. Specifically, at the scheduling layer, makespan is adopted as the core objective, and a cross-slot load fluctuation factor is designed to quantify spatiotemporal contention and constrain the worst-case completion time. For state modeling, a multi-granularity representation mechanism integrates graph neural networks (GNNs) and large language models (LLMs) to capture both instantaneous interactions and long-term evolution. For decisio-nmaking, the Maxvar-DDQN framework employs multiple Double Q-networks with variance-based confidence regulation to ensure stable and robust offloading under asynchronous task flows. Extensive experiments show that HCAO achieves the best trade-off between makespan and load balance, demonstrating superior scalability and robustness across dynamic IoLoUA systems.

With the rapid development of industrial automation, few-shot object detection has emerged as a promising solution for recognizing novel categories using only limited annotated data. However, existing approaches often suffer from high computational complexity and limited adaptability when deployed in resource-constrained industrial environments. To achieve precise detection, efficiency, and security, this article proposes a collaborative computing framework based on an edge-cloud dual-prototype graph convolutional network (EC-DP-GCN) for few-shot object detection with hierarchical knowledge embedding. The framework comprises three key components: a device-EC architecture, a positive-negative prototype (PNP) module, and a class-prototype-sample-driven hierarchical graph (CPS-HG) module. Specifically, the PNP module explicitly models intraclass diversity by constructing discriminative positive and negative prototypes from limited support samples, thereby enhancing prototype representativeness. In addition, we further introduce the CPS-HG module, which treats the dual prototypes as class-based prior knowledge and models the relationships among samples through a hierarchical graph structure encompassing class, prototype, and sample levels. This design effectively expands the semantic margins in the embedding space to improve knowledge-guided detection. Extensive experiments on the PASCAL VOC and MS COCO benchmarks demonstrate that EC-DP-GCN significantly outperforms strong baselines and previous state-of-the-art methods, achieving an average improvement of 1.1% in 10-shot detection scenarios.

The security of UAV communications is one of the crucial aspects in UAV networks due to the increasing use of UAVs in various applications. In this paper, a novel approach based on Post Quantum Cryptography (PQC) is proposed to improve the security of UAV communications. The proposed approach utilizes the N-th Degree Truncated Polynomial Ring Unit (NTRU) algorithm, integrated with Blockchain Technology (BT) and the Message Queuing Telemetry Transport Protocol (MQTT). In the proposed approach, UAVs are authenticated by the server, and the BT ledger stores the UAV information, such as its identification number and public key. The encryption and decryption of the message is performed using a securely established secret key between the sender and the receiver UAV. The results of the proposed approach are evaluated and compared with other existing PQC algorithms. The results show that the proposed approach is more computationally efficient and faster than other algorithms.

The next generation of mobile networks is moving artificial intelligence out of a sporadic implementation model and into the managed service paradigm, which requires careful placement, scaling, validation and security of the radio, edge and cloud space. Although federated learning is vulnerable to meet strict privacy requirements, its training process has the properties of a functional service chain, which includes transient participation and intermittent client interactions, competitive service slices, and the need to implement trust and comply with latency and reliability requirements. Secure federated intelligence is described as an orchestrated 6G-optimized service graph in this research, which includes: (i) slice-aware admission and resource assignment; (ii) trust-gated robust aggregation; and (iii) post-quantum secure update exchange as composable tasks. An orchestration workflow with a feasibility-first constraint is planned to maintain constraints at the service level and also ensure the convergence in case of heterogeneous participation and adversity of poisoning. Large scale simulation of three different 6G slice formats illustrate a steady decrease in tail latency and SLA breaches, an improved resistance to malicious clients, and a relatively low control overhead, thus supporting the feasibility of the federated modelling to federated managed service transition.

The rapid growth of the Internet of Things (IoT) deployments has resulted in a massive volume of data generated by smart devices equipped with sensors. The data is typically offloaded to cloud services for convenient and efficient sharing among multiple receivers. However, such cloud-provided encryption mechanisms impose computational burdens on resource-limited IoT hardware and raise data integrity concerns among users. Searchable public key encryption (SPKE) primitive mitigates these issues by ensuring confidential and secure data retrieval. However, existing SPKE approaches in the literature include several critical limitations, including reliance on heavy pairing operations and key-generation authorities, lack of forward secrecy preservation, and support for verifiable ciphertext retrieval in third-party cloud environments. Addressing these concerns, we propose an effective certificateless searchable encryption scheme utilizing standard elliptic curve primitives that eliminates certificate management and key-escrow concerns while avoiding costly pairings. Our construction effectively mitigates information leakage from search queries and access patterns, while incorporating forward-secure verifiable ciphertext retrieval. Additionally, it achieves crucial security guarantees, including ciphertext and trapdoor indistinguishability under adaptive chosen-keyword attacks while also resisting major adversarial threats. Furthermore, comprehensive theoretical and performance evaluations demonstrate the proposed scheme’s efficiency and functional superiority over existing approaches.

Diabetic Retinopathy (DR) is a prominent results of diabetes mellitus that causes abnormalities lesions in retina. If not identified at early, it may progress to complete loss of vision. Unfortunately, DR is an irreversible, and treatment only sustains existing vision. Timely detection and accurate treatment of DR can considerably decrease the chance of blindness. Manual diagnosis of DR in retinal fundus images (RFIs) by ophthalmologist is time consuming, costly and laborious tasks with a higher risk of misdiagnosis. Recently, Deep learning (DL) has gained popularity and shown remarkable performance particularly in medical image analysis and classification. Convolutional neural networks (CNNs) are increasingly being used as a DL approach in medical image analysis, and they are very efficient. This manuscript offers the design of Falcon Optimizer with Ensemble of Deep Learning Algorithm Assisted Diabetic Retinopathy Diagnosis Model (FOEDLA-DRDM)  system on RFIs. The FOEDLA-DRDM system employs a Wiener filtering (WF) based preprocessing approach to eliminate noise from images. Following this, FOEDLA-DRDM system leverages the SE-DenseNet method to generate the feature vectors. For DR recognition FOEDLA-DRDM system applies an ensemble approach that combines - AutoEncoder, long short-term memory (LSTM), and deep belief network (DBN). Finally, Falcon Optimizer (FO) adjusts the hyperparameter values of the ensemble approach, giving rise to classification efficiency. The FOEDLA-DRDM system is validated by simulating it on a Kaggle DR dataset, with results being measured according to various criteria. The simulation findings showcase the effectiveness of the FOEDLA-DRDM system in diagnosis of DR.

Hydrological flow forecasting is critical for water resource management, disaster early warning, and ecological protection. However, centralized modeling approaches face persistent challenges with data heterogeneity, scarcity of extreme-event samples, and privacy constraints. This manuscript demonstrates a novel paradigm for fusing heterogeneous, distributed hydrological data while preserving privacy, creating a more robust and globally informed model than possible with isolated data silos. We propose Federated Learning Multi-Stations Fusion (FedMSF), which integrates local models with global aggregation to handle cross-basin variability without exposing raw data. A proximal term reduces training bias under distributional shifts, and a Multi-Objective Aggregation strategy (FedMOA) adaptively weights clients to enhance structural consistency. Additionally, extreme-aware data augmentation enriches the representation of rare events, while an AI-driven large language model (LLM) guides hyperparameter optimization. All reported metrics represent the mean performance across all catchments. Experiments on the CAMELS-GB West region show that FedMOA achieves RMSE of 0.4322, MAE of 0.2358, and NSE of 0.8371, outperforming existing methods by 7.93 %, 9.20 %, and 7.83 %, respectively. Furthermore, KGE improves by 4.48 % to 0.8127, while FLV and FHV decrease by 24.38 % and 34.7 %, respectively, indicating a reduction in volumetric errors. With the integration of augmentation and LLM-driven optimization, FedMSF further enhances performance, reaching an NSE of 0.8406, demonstrating improved robustness and generalization in cross-regional hydrological forecasting.

Intelligent Transportation System (ITS) employs traditional optimization methods, including gradient-based or evolutionary methods. These methods often fail to simultaneously balance predictive accuracy, latency, and resource efficiency while respecting strict operational constraints. Multi-objective system design under explicit constraints is also a challenge in engineering and artificial intelligence. To address these gaps, we propose a Transfer Learning-Enhanced Multi-Objective Whale Optimisation Algorithm (TL-MOWOA) for constrained multi-objective optimisation of control parameters in Intelligent Transportation Systems (ITS). The framework integrates transfer learning to accelerate convergence by reusing knowledge from related optimisation tasks. In this way, it improves adaptability across diverse traffic scenarios. Evolutionary operators of the Whale Optimisation Algorithm, within the TL-MOWOA Algorithm, preserve population diversity and ensure robust global search. The transfer-learned priors guide the search toward promising feasible regions, hence reducing the risk of stagnation. Experimental evaluation was conducted on synthetic benchmarks, including balanced and high-dimensional constrained. The results signify that the TL-MOWOA Algorithm better for state-of-the-art algorithms. The proposed TL-MOWOA Algorithm achieves up to 15% reduction in average travel time, 12% reduction in fuel consumption, 20% reduction in congestion index, and 18% reduction in emissions as compared to NSGA-III, MOPSO, MOWOA, and standalone TL-based EAs. The proposed TL-MOWOA Algorithm provides a scalable and adaptive solution for ITS optimisation.

There is an explosive growth of intelligent devices in the IoT ecosystem over the years. Owing to the massive multiple access at the network edge, there is increased latency and transmission overhead. Multiaccess edge computing (MEC) is a key technology used to offload the wireless devices from the computational tasks. But the wireless signal propagation is subject to fading, attenuation, obstructions, and other disturbances thereby affecting the performance of edge network. Reconfigurable intelligent surface (RIS) technology improves the quality of wireless propagation links through controlled reflection. This article presents an RIS-aided framework for a heterogenous edge network to offload the computation tasks of the resource constraint user equipment to the small access points (APs). A resource control algorithm is proposed which enables selection of an RIS-AP pair for each node in the edge network. The proposed algorithm selects the RIS-AP pair using maximum channel gain criteria such that the system sum throughput is maximized. Also, enabling reflection through the multiple RISs, the shortest path is selected using the graph theory to obtain the tradeoff between latency and reflection loss. It is observed that the proposed approach improves the achieved sum throughput of the system by 21.7% and the latency is reduced by 13.8%. The network performance is evaluated for varied RIS size and number of reflecting elements under different RIS phase shift design. It is shown that RIS with 1000 reflecting elements each of size (lambda/2)x(lambda/2) with equal phase shifts achieve sum throughput gain of 25.2% over randomly chosen phase shifts. Further, the comparison of intelligent reflecting the surface-aided MEC system with the conventional MEC system and the clustered MEC system is performed.

Cloud-based Intelligence of Things is significant for Augmented Enterprise Management Systems. Data integrity auditing is challenging in the intelligence of things environment, mainly when the newer versions in the public cloud environment update existing encrypted data. The related literature on cloud-based intelligence relies on encrypted data uploading or locally handling encryption and decryption using user keys. Considering the security risk, storage constraints at the edge, and realtime environment, both approaches have limited applicability in the intelligence of things environment. This paper presents the Privacy-Aware Secure Data Auditing (PASDA) framework at the cluster head for online data integrity verification. Specifically, the users hide data files by the blinding process with a generation of their corresponding signatures, which achieves data auditing by utilizing homomorphic techniques. A novel automated self-triggering/ Self-auditing-based data integrity auditing system is proposed, which detects the changes made in the cloud-stored data and sends alert messages to the trusted primary cloud server and users. A data dynamics method is developed containing a timestamp with a pointer to store multiple versions of the same file without signatures re-generation for the whole same file. The user is revoked due to prolonged absence or detection of the missed behaviour with system or service expiry. With these data dynamics, the proposed PASDA framework allows CH to regenerate signatures of the revoked user using its membership key for cloud-based stored data access and data integrity auditing. In-depth security analysis and extensive simulations based on comparative performance evaluation attest to the benefits of the proposed PA