TNSM Searchable Index

Author(s)	Title	Year	Publication	Keywords
Dena Markudova, Michela Meo	Advancing Congestion Control for Real-Time Communications with Reinforcement Learning: the ReCoCo framework	2026	Early Access	Feeds Broadcasting Circuits	Real-Time Communication (RTC) applications such as video conferencing and cloud gaming are used daily for both work and leisure. With the ever-growing need of better quality video and audio, comes the necessity for novel Congestion control algorithms that optimize the channel bandwidth usage and improve the Quality of Experience (QoE) of users. Since RTC typically operates over UDP, congestion control is implemented at the application layer, enabling the deployment of advanced adaptive algorithms. In this paper, we propose ReCoCo, a fully Reinforcement Learning (RL)-based congestion control solution for RTC. ReCoCo leverages receiver-side network statistics to predict short-term bandwidth dynamics and adapt the sender's rate accordingly. We train the model using 162 heterogeneous bandwidth traces and evaluate it on more than 3000 additional unseen traces to assess generalization. We benchmark ReCoCo against four state-of-the-art RTC congestion control algorithms and find that it outperforms them in QoE by 14% - 34% on the training data and 3% - 20% on the test data. The gains stem primarily from improved bandwidth utilization, while maintaining competitive delay variation and negligible packet loss. Beyond aggregate performance, we analyze robustness across diverse bandwidth regimes to ensure stable behaviour. These results demonstrate that large-scale trace-driven RL training can produce congestion control policies that generalize effectively across heterogeneous network conditions, offering a practical and deployable alternative to heuristic-based approaches.	10.1109/TNSM.2026.3683265
Krati Mittal, Akash Gupta, Parul Garg	Resource Management in Energy Efficient RSMA based Hybrid Satellite Terrestrial Network	2026	Early Access		In this paper, we study resource management in terms of energy and spectrum for a cooperative satellite terrestrial network. We investigate a comprehensive analysis of an energy efficient rate splitting multiple access (RSMA) based cooperative satellite terrestrial network. RSMA being more efficient both in terms of energy and spectrum when combined with practical non linear energy harvesting, results in a highly efficient cooperative network. While analyzing the network, we consider that the energy of the signal transmitted by the satellite is non linearly harvested at decode and forward (DF) relay. Further this harvested energy is used to transmit signal from relay to RSMA users. The satellite to relay link is characterised by shadowed Rician fading while the link between relay and RSMA users is characterised by α-μ fading. We derive the closed form expression of outage probability and ergodic capacity considering the impact of key parameters both numerically and asymptotically. Simulation results validate the numerical results obtained.	10.1109/TNSM.2026.3684366
Cheng Ren, Jinsong Gao, Yu Wang, Yaxin Li, Hongwei Li	GCN-Transformer Assisted Live SFC Migration with Hierarchical Reinforcement Learning in Mobile Edge Computing	2026	Early Access	Feeds Antennas Filtering theory	Empowered by network function virtualization (NFV), mobile edge computing aims to provide low latency and ultra reliable network services to mobile end users, achieved as a service function chain (SFC) consisting of a series of ordered virtual network functions (VNFs). Due to user mobility, live SFC migration is imperative to avoid Quality of Service (QoS) degradation. Recent advances mainly make separate decisions on VNF node remapping and migration path routing in a heuristic manner, or implement both through reinforcement learning within a single agent of ill-defined policy and action space. In this paper, given next access node, we first formulate the live SFC migration problem as an integer linear programming (ILP) model to achieve optimal solutions. Then, we present HRL-QC, a hierarchical reinforcement learning framework that jointly optimizes VNF destination node remapping, migration path and post-migration service path selections for QoS-aware and cost-efficient live SFC migration. A GCN-Transformer block is introduced to capture long-range VNF-to-physical node dependencies, while a two-level actor-critic design couples the decision-makings through inter-level reward passing. Extensive evaluations show that HRL-QC outperforms the state-of-the-art in energy consumption, migration time, end-to-end service delay, and migration success rate, while remaining within a small margin of the optimal ILP solution.	10.1109/TNSM.2026.3681690
Qi He, Xiao-Jian Li	Secure state estimation for Cyber-Physical systems under composite attacks	2026	Early Access	Antennas Antenna arrays Kalman filters	This paper is concerned with the secure state estimation problem for Cyber-Physical system under composite attacks, which will simultaneously include adversarial injections and missing sensor measurements. The maximum rank deficiency number of the so-called generalized observability matrix is constructed to formulate the computable correctable conditions, which also improve the existing conclusions developed for the single injection case. Especially, an active defense strategy is established based on the derived necessary and sufficient correctable conditions, thus the success rate of secure estimation for Cyber-Physical system can be effectively improved by about 20% in the experiments. The designed `1-norm decoder outperforms the Robust Kalman filters (RKF) in secure estimation performance against the composite attacks with large-amplitude sparse injections. The estimation errors can be reduced more than 30% in simulations. Compared with the mixed norm decoder, the running time of solving convex optimization problem can be further reduced. The simulations of random control systems and IEEE 14-bus electric power grid are carried out respectively, which verify the feasibility of secure state estimation under composite attacks and the advantages of proposed scheme.	10.1109/TNSM.2026.3683412
Md Arif Hassan, Bui Duc Manh, Cong T. Nguyen, Chi-Hieu Nguyen, Dinh Thai Hoang, Diep N. Nguyen, Nguyen Van Huynh, Dusit Niyato	SBW 3.0: A Blockchain-Enabled Framework for Secure and Efficient Information Management in Web 3.0	2026	Early Access	Jamming Protocols Semantic Web	In this paper, we propose an effective blockchain-enabled information management framework, named Smart Blockchain-based Web 3.0 (SBW 3.0). Our framework aims to handle information within Web 3.0 efficiently, enhance data security and privacy, create new revenue streams, and encourage users to contribute valuable information to websites. To this end, SBW 3.0 employs blockchain technology and smart contracts to manage the decentralized data collection in Web 3.0. Moreover, we introduce a robust consensus mechanism grounded in Delegated Proof-of-Stake (DPoS) to reward user contributions. Furthermore, we develop a non-cooperative game model to examine user behavior in this context and conduct thorough analysis to prove the uniqueness of the Nash equilibrium in our proposed system. Through simulations, we evaluate the performance of SBW 3.0 and analyze the effects of various critical parameters on information contribution. Our results validate the theoretical analysis, showing that the proposed consensus mechanism successfully encourages nodes and users to provide more information, thus overcoming the current limitations of Web 3.0 regarding data decentralization and management.	10.1109/TNSM.2026.3683881
Venkatesan C, Jeevanantham S, Rebekka B	Credibility-Aware Hierarchical Blockchain Consensus Protocol for Bandwidth-Limited IoT Edge Networks	2026	Early Access	Payloads Military aircraft Space technology	The Internet of Things (IoT) edge networks are widely accompanied by blockchain for the associated benefits namely, transparency, reliability and security. Especially, the consensus mechanism is the integral part of the blockchain to attain the common agreement among the nodes. The practical impediments associated with this synergy are scalability, network overhead, fault tolerance, and computational resource constraints. Thus, to surmount these issues, we propose a novel Heirarchical Proof of Credibility (HPoC) consensus protocol incorporating the randomization of miner through Physical Layer Key (PLK). Unlike existing works, the orchestration of node responsibilities in hierarchy is dynamic based on the node’s malicious behavior during mining process. Further, the Shulze beatpath method-based penalization of the byzantine voting behavior is introduced. The proposed HPoC is evaluated on the Long Range (LoRa) Wide Area Network (WAN) for validating its performance in the presence of resource constraints. The HPoC shortens the consensus latency by 76.4%, 42.5%, 30.5%, 30.98%, 35.84% and 3.7% with respect to Proof of Work (PoW), Practical Byzantine Fault Tolerance (PBFT), RAFT, Reputation Awareness Randomization Consensus (RARC), Reputation-based Secure HotStuff (RSHS), and Proof-of-Physical-Layer-Authentication (PoPLA) respectively. The HPoC surpasses existing schemes by reducing the communication cost significantly while tolerating half of the nodes being byzantine nodes.	10.1109/TNSM.2026.3683555
Zhenzhen Yan, Lizhi Peng, Peiqiang Liu, Yingshuo Bao, Bo Yang	NT-Transformer: A Non-Pretrained Encrypted Network Traffic Classification Model	2026	Early Access	Payloads Military aircraft Space technology	Network traffic classification plays an indispensable role in network management, Quality of Service (QoS), and cybersecurity. With the widespread encryption techniques applied to network traffic, it has become increasingly challenging to classify network traffic into different management groups accurately. In recent years, pre-training Transformer-based models have been successfully applied to Natural Language Processing (NLP), and researchers have also introduced such models into encrypted network traffic analysis. However, besides the similarities of words in NLP and byte codes in network traffic, there exist essential differences between them, which may cause inefficacy of the pretrained model when being applied to new traffic data. In this paper, we propose a non-pretrained encrypted network traffic classification model based on Transformer called NT-Transformer, which can directly learn labeled network traffic features at two levels of granularity, namely, byte level (uni-gram or bi-gram) and flow level (packet size and packet inter-arrival time), without the relatively expensive pre-training procedure of unlabeled data. This method is validated on three public datasets and three sets of recently collected network traffic data. Experimental results indicate that in some scenarios, pretrained models offer limited performance gains when applied to new encrypted network traffic data not encountered during pretraining, and NT-Transformer with uni-gram byte representation outperforms the state-of-the-art models in terms of pushing the F1 score up by 0.25% - 2.24%.	10.1109/TNSM.2026.3683410
Jing Zhang, Chao Luo, Rui Shao	MTG-GAN: A Masked Temporal Graph Generative Adversarial Network for Cross-Domain System Log Anomaly Detection	2026	Early Access	Anomaly detection Adaptation models Generative adversarial networks	Anomaly detection of system logs is crucial for the service management of large-scale information systems. Nowadays, log anomaly detection faces two main challenges: 1) capturing evolving temporal dependencies between log events to adaptively tackle with emerging anomaly patterns, 2) and maintaining high detection capabilities across varies data distributions. Existing methods rely heavily on domain-specific data features, making it challenging to handle the heterogeneity and temporal dynamics of log data. This limitation restricts the deployment of anomaly detection systems in practical environments. In this article, a novel framework, Masked Temporal Graph Generative Adversarial Network (MTG-GAN), is proposed for both conventional and cross-domain log anomaly detection. The model enhances the detection capability for emerging abnormal patterns in system log data by introducing an adaptive masking mechanism that combines generative adversarial networks with graph contrastive learning. Additionally, MTG-GAN reduces dependency on specific data distribution and improves model generalization by using diffused graph adjacency information deriving from temporal relevance of event sequence, which can be conducive to improve cross-domain detection performance. Experimental results demonstrate that MTG-GAN outperforms existing methods on multiple real-world datasets in both conventional and cross-domain log anomaly detection.	10.1109/TNSM.2026.3654642
Qingyang Zhang, Siqi Fu, Jie Cui, Fengqun Wang, Jiaxin Li, Hong Zhong	Forward Secure Data Sharing Based on Proxy Re-Encryption in Industrial Internet of Things	2026	Early Access	Broadcasting Broadcast technology Central Processing Unit	In the Industrial Internet of Things (IIoT), data is shared among different production segments for collaborative production. However, industrial production processes often involve corpus sensitive information, and during data sharing, every flow of data between different subjects increases its exposure to vulnerabilities. Proxy re-encryption offers a practical approach to enabling secure data exchange, thereby partially mitigating the tension between information sharing and privacy protection. Many scholars have proposed data-sharing schemes utilizing proxy re-encryption technologies. However, existing schemes still face issues, such as excessive communication and computational overhead, and cannot guarantee forward security. Therefore, this study proposes a lightweight and forward-secure data-sharing scheme. First, the proxy generates the re-encryption key, substantially alleviating the overhead on the data owner. Second, whenever the time node changes or a data user is revoked, the data user loses access to historical data, which effectively ensures forward security. The security proof confirms the scheme’s IND-CPA security under the DBDH assumption. Performance analyses reveals that the proposed scheme achieves higher security in data sharing with a lower computational overhead.	10.1109/TNSM.2026.3683581
Kexian Liu, Jianfeng Guan, Su Yao, Ilsun You, Hongke Zhang	OMEGA: A Comprehensive Cloud-Edge-Device Authentication and Key Agreement Scheme for Collaborative Multi-Factory Manufacturing in IIoT	2026	Early Access	Radio broadcasting Frequency modulation Central Processing Unit	Cloud Manufacturing (CMfg) has revolutionized traditional manufacturing by enabling resource sharing across factory boundaries. As industry increasingly adopts cloud-edge-device collaborative ecosystems, effective authentication and key agreement (AKA) mechanisms play a critical role in safeguarding security across these complex multi-factory environments. Existing schemes, however, focus primarily on isolated binary security relationships (e.g., device-edge, device-cloud, or edge-cloud pairs individually), neglecting the integrated cloud-edge-device collaborative security demands inherent in multi-factory environments, while often relying on trusted authorities and high-overhead cryptographic mechanisms. This leads to redundant authentication processes, increased latency, and security vulnerabilities as devices must separately establish connections with each entity. To bridge these gaps, this paper introduces OMEGA: a comprehensive Cloud-Edge-Device Authentication and Key Agreement scheme for collaborative multi-factory manufacturing that pioneers an integrated security architecture. OMEGA’s distinctive advantage lies in its ability to establish all necessary secure connections (device-edge, device-cloud, and edge-cloud) through a single authentication request from the smart manufacturing device (SMD), significantly reducing authentication overhead. By leveraging lightweight hash operation, OMEGA creates a cohesive security fabric that enables SMDs to concurrently access specialized capabilities from multiple clouds while leveraging edge computing for time-sensitive operations. Security analysis using both Real-Or-Random (ROR) model and ProVerif formal verification tool demonstrates OMEGA achieves robust security while performance evaluation confirms its superior efficiency in industrial environments.	10.1109/TNSM.2026.3683347
Xinyue Zhang, Xuan Zhou, Jie Ma, Zeqi Li, Feng He	Interference-Aware Multi-Metric Delay Evaluation and Optimization for Switched Networks	2026	Early Access	Aerospace electronics Aerospace engineering Radio broadcasting	Switched networks are essential to modern real-time systems, where packet delays must be tightly bounded with minimal variation. Traditional delay analysis often focuses on worst-case bounds, but may overlook delay jitter induced by fine-grained inter-flow interference, which can degrade real-time performance and stability. Existing routing schemes typically rely on proxy indicators such as link load or path length, offering limited explicit control over delay and jitter behavior. To address these limitations, we propose an interference-aware delay evaluation and optimization framework that models the encounter interval and magnitude of flow interference at the packet level. From this, we derive worst-case delay, average delay, and delay jitter, and integrate these metrics into a unified, tunable optimization objective. We design a K-shortest-path genetic algorithm to jointly reduce them. Experimental results over multiple traffic loads demonstrate consistent improvements in delay and jitter performance, indicating that the proposed approach is scalable and practical for delay-sensitive and stability-critical switched networks.	10.1109/TNSM.2026.3680250
Jiajia Du, Songtao Liu, Cheng Zhi, Junfan Zhao, Hua Wu, Guang Cheng	TunnelEye: An Explainable Framework for Real-Time Detection of Malicious DoH Traffic in High-Speed Backbone Networks	2026	Early Access	Payloads Military aircraft Space technology	Since plaintext DNS queries are vulnerable to eavesdropping and tampering, encrypted DNS protocols such as DoH (DNS over HTTPS) have been widely adopted. However, attackers can exploit DoH by hiding malicious DNS requests and responses in HTTPS traffic, enabling covert communication and evading detection. Existing methods rely on generic bidirectional traffic statistics that lack interpretability, are costly to compute, and may become unavailable or unstable in backbone monitoring nodes with massive unidirectional and sampled traffic. To address these issues, we propose TunnelEye, an explainable real-time framework for malicious DoH detection. It uses protocol-level behavioral analysis to capture DoH features that remain stable across traffic directions and sampling rates, and introduces an efficient data structure, DoH-Sketch, to ensure real-time performance. Experiments on public and self-collected datasets show that TunnelEye enables second-level detection with high accuracy. On public datasets, it achieves 99.88% accuracy. In backbone networks with sampled traffic, TunnelEye outperforms existing methods, improving accuracy by 14.5% at a 1/128 sampling rate and reducing the false positive rate by 31% under interference from background traffic.	10.1109/TNSM.2026.3682686
Yingpu Nian, Xiang Jia, Baishun Zhou, Zhi Wang, Bo Yi, Xinhao Zhou, Haodong Li, Yuan Yang, Xingwei Wang, Geyong Min, Keqin Li	XAForward: Accelerating Distributed Large-scale Language Model Training Through Fast eXpress Data Path	2026	Early Access		With the rapid development of Artificial Intelligence Generated Content (AIGC), single data centers are increasingly unable to meet the growing demands for data and computational resources in distributed large-scale language model (LLM) training. In this context, distributed training across heterogeneous data centers has become a necessary choice to enhance computational power and flexibility. However, the networks in heterogeneous data centers are polymorphic, with diverse communication protocols and network architectures. This heterogeneity renders traditional routing devices ineffective in recognizing and processing gradient data. Moreover, frequent copying and excessive parsing of gradient data by routing devices across heterogeneous data centers significantly increase model training time. To address these challenges, we propose XAForward, a method for accelerating distributed LLM in heterogeneous data centers using eXpress Data Path (XDP). Specifically, XAForward introduces a polymorphic-compatible protocol that reconstructs the header of gradient data packets to enable efficient data forwarding across different communication protocols in heterogeneous data centers. Additionally, to accelerate distributed LLM computing and reduce gradient data copying and excessive parsing during training, XAForward leverages kernel-bypass techniques based on XDP for packet processing and kernel-level data forwarding using network index identifiers. Experimental results show that, compared to state-of-the-art methods, XAForward reduces the distributed LLM training time by approximately 35% to 40%.	10.1109/TNSM.2026.3684024
Zuodong Wu, Dawei Zhang, Mianxiong Dong, Kaoru Ota	PDRAA: An Efficient Privacy Data Retrieval Protocol with Anonymous Authorization Based on Verifiable Credential	2026	Early Access	Payloads Broadcasting Broadcast technology	In the data-driven era, the unchecked collection and processing of personal data has given rise to serious privacy concerns. In response, the General Data Protection Regulation (GDPR) was introduced to grant individuals stronger control over the use of their data. Privacy data retrieval methods show considerable promise in this context, but further improvements are required to balance the principles of lawfulness and data minimization. To address this problem, we propose PDRAA, an efficient privacy data retrieval protocol with anonymous authorization based on the verifiable credential (VC). Specifically, our designed VC achieves anonymous identification of data subjects and facilitates fine-grained access control by supporting selective disclosure of attributes. By combining VC with non-interactive zero-knowledge (NIZK) proofs, PDRAA enables data subjects to anonymously authenticate via VC presentation. This allows the data controller to verify the legitimacy of retrieval requests while ensuring compliance with the principle of data minimization. Besides, PDRAA introduces a re-randomization mechanism to prevent linkability attacks during the authorization process and provides lightweight, flexible authorization revocation. Moreover, we utilize Labeled Private Set Intersection (Labeled PSI) technology to meet the privacy requirements of participants and support batch retrieval. Our protocol takes a comprehensive security analysis within the Universal Composability framework. Experimental results demonstrate that PDRAA outperforms existing methods in terms of performance, which is significant for promoting compliance with GDPR.	10.1109/TNSM.2026.3681957
Deemah H. Tashman, Soumaya Cherkaoui	Trustworthy AI-Driven Dynamic Hybrid RIS: Joint Optimization and Reward Poisoning-Resilient Control in Cognitive MISO Networks	2026	Early Access	Reconfigurable intelligent surfaces Reliability Optimization	Cognitive radio networks (CRNs) are a key mechanism for alleviating spectrum scarcity by enabling secondary users (SUs) to opportunistically access licensed frequency bands without harmful interference to primary users (PUs). To address unreliable direct SU links and energy constraints common in next-generation wireless networks, this work introduces an adaptive, energy-aware hybrid reconfigurable intelligent surface (RIS) for underlay multiple-input single-output (MISO) CRNs. Distinct from prior approaches relying on static RIS architectures, our proposed RIS dynamically alternates between passive and active operation modes in real time according to harvested energy availability. We also model our scenario under practical hardware impairments and cascaded fading channels. We formulate and solve a joint transmit beamforming and RIS phase optimization problem via the soft actor-critic (SAC) deep reinforcement learning (DRL) method, leveraging its robustness in continuous and highly dynamic environments. Notably, we conduct the first systematic study of reward poisoning attacks on DRL agents in RIS-enhanced CRNs, and propose a lightweight, real-time defense based on reward clipping and statistical anomaly filtering. Numerical results demonstrate that the SAC-based approach consistently outperforms established DRL base-lines, and that the dynamic hybrid RIS strikes a superior trade-off between throughput and energy consumption compared to fully passive and fully active alternatives. We further show the effectiveness of our defense in maintaining SU performance even under adversarial conditions. Our results advance the practical and secure deployment of RIS-assisted CRNs, and highlight crucial design insights for energy-constrained wireless systems.	10.1109/TNSM.2026.3660728
Arad Kotzer, Tom Azoulay, Yoad Abels, Aviv Yaish, Ori Rottenstreich	SoK: DeFi Lending and Yield Aggregation Protocol Taxonomy, Empirical Measurements, and Security Challenges	2026	Early Access	Filtering Application specific integrated circuits Filters	Decentralized Finance (DeFi) lending protocols implement programmable credit markets without intermediaries. This paper systematizes the DeFi lending ecosystem, spanning collateralized lending (including over- and under- collateralized designs, and zero-liquidation loans), uncollateralized primitives (e.g., flashloans), and yield aggregation protocols which allocate capital across underlying lending platforms. Beyond a taxonomy of mechanisms and comparing protocols, we provide empirical on-chain measurements of lending activity and user behavior, using Compound V2 and AAVE V2 as case studies, and connect empirical observations to protocol design choices (e.g., interestrate models and liquidation incentives). We then characterize vulnerabilities that arise due to notable designs, focusing on interestrate setting mechanisms and time-measurement approaches. Finally, we outline open questions at the intersection of mechanism design, empirical measurement and security for future research.	10.1109/TNSM.2026.3682174
Kang Liu, Jianchen Hu, Donglai Ma, Xiaoyu Cao, Yuzhou Zhou, Lei Zhu, Li Su, Wenli Zhou, Xueqi Wu, Feng Gao	Topology-Aware Virtual Machine Placement through the Buffer Migration Mechanism	2026	Early Access	Central Processing Unit Filtering Filters	The virtual machine (VM) placement considering the topology constraints is difficult because the unpredictable topological VMs raise additional structural requirements (including the affinity, anti-affinity and fault-domain) on the resource pool. Thus, the service level agreement (SLA) can be violated even when the occupancy of the resource pool is quite modest. In order to solve this problem, we propose an efficient buffer-migration-based heuristic online algorithm. First, we build an integer programming model for the topology-aware VM placement problem. Second, we propose a hierarchical resource-preserving online approach, where the Rack and physical machine (PM) nodes are selected in the upper and lower layers respectively. Finally, we utilize the buffer to place and migrate the unfitted VMs to enhance the capacity of the resource pool. The proposed approach is tested with high proportional topological VM requests (nearly 60%) in the resource pool with the scale of 500, 1000 and 1500 PMs. The results show that our online approach (with unknown upcoming VM information) can achieve more than 85% of the performance for the offline approach (with complete upcoming VM information). The latency is lower than 5ms per VM.	10.1109/TNSM.2026.3678976
Wangqing Luo, Jinbin Hu, Hua Sun, Pradip Kumar Sharma, Jin Wang	SALB: Security-Aware Load Balancing for Large Language Model Training in Datacenter Networks	2026	Early Access	Training Load management Packet loss	To meet the massive compute and high-speed communication demands of Large Language Model (LLM) training, modern datacenters typically adopt multipath topologies such as Fat-Tree and Clos to host parallel jobs across hundreds to thousands of GPUs. However, LLM training exhibits periodic, high-bandwidth communication patterns. Existing load-balancing schemes become misaligned under dynamic congestion and anomalous surges: they struggle to promptly mitigate iteration-peak congestion and lack effective isolation of anomalous traffic. To address this, we propose Security-Aware Load Balancing (SALB) for LLM training. SALB leverages a Deep Reinforcement Learning (DRL) controller with queue and delay signals for packet-level multipath load balancing and employs path binding to confine suspicious flows. By integrating data security into load balancing, SALB simultaneously achieves high throughput and robust traffic isolation. NS-3 simulation results show that, compared with CONGA, Hermes, and ConWeave, SALB reduces the 99th-percentile flow completion time (FCT) of short flows by an average of 65% and increases the throughput of long flows by an average of 54%. It further outperforms the baselines in aggregate throughput, path utilization, and packet loss rate, thereby significantly enhancing system stability, robustness, and data security.	10.1109/TNSM.2026.3678979
Vibha Jain, Prabal Verma, Mohit Kumar, Aryan Kaushik	Blockchain-enabled Incentive Mechanism for Federated Learning: A Multi-Agent Deep Deterministic Policy Gradient Approach	2026	Early Access	Broadcasting Broadcast technology Central Processing Unit	The expeditious growth of the Internet of Things (IoT) generates massive data, which allows advanced machine learning. However, the traditional approach of centralized model training raises the issue of high bandwidth consumption and privacy. Federated learning (FL) mitigates this by enabling local training on raw data with centralized aggregation to generate the global model. The effectiveness of FL depends upon the active participation of resource-constrained local devices. This article presents a blockchain-enabled incentive mechanism for FL leveraging the Multi-Agent Deep Deterministic Policy Gradient (MA-DDPG) algorithm. Specifically, an incentive scheme is formulated with the MEC (Mobile Edge Computing) server as the leader agent and local devices as learning agents in a cooperative environment. We formalize a two-stage Stackelberg game to establish a Nash equilibrium, which ensures fair and utility-optimized reward distribution for MEC and devices. A Markov Decision Process (MDP) is utilized to solve the equilibrium with incomplete knowledge, and utilities are optimized using the MA-DDPG algorithm. The proposed model considers data quality and device contribution to obtain optimal reward distribution and participation strategies dynamically. The experimental results show an approximate 38% improvement in MEC utility and approx 17% in device utility, with rapid convergence (approximately 300-500 episodes) at a learning rate of 0.0001.	10.1109/TNSM.2026.3682129
Can Wang, Run-Hua Shi, Jiang-Yuan Lian, Pei-Xuan Wang, Ze-Hui Jiang	Quantum-Enhanced Matching Mechanism for Secure and Efficient Power IoT Data Trading	2026	Vol. 23, Issue	Protocols Photonics Databases	The exponential growth of power IoT data has created immense potential for intelligent energy management, but it also presents critical challenges in achieving secure and efficient data trading. In particular, emerging data trading scenarios demand support for range nearest neighbor matching, which current schemes fail to address. This paper proposes a novel quantum trading matching scheme tailored for power data markets, which, for the first time, supports range nearest neighbor matching while balancing accuracy, efficiency, and privacy. To improve matching efficiency, we design a quantum private query (QPQ) mechanism based on a bidirectional sliding window (BSW), which replaces traditional linear search with dynamic range expansion. Furthermore, to ensure strong privacy and security in real-world scenarios, we develop a two-layer QPQ framework that performs data feature matching and identity retrieval separately, supported by a customized key distribution strategy. Our solution resists quantum attacks and significantly reduces computational overhead. At the same time, by utilizing non-ideal photon sources, it offers a practical and privacy-preserving solution for large-scale power data trading and matching.	10.1109/TNSM.2026.3667701