TNSM Searchable Index

Author(s)	Title	Year	Publication	Keywords
Kunpeng Zheng, Huibin Zhang, Yongli Zhao, Yuan Cao, Wei Wang, Xin Li, Zhuangzhuang Ma, Lihan Zhao, Jie Zhang	Sun-Outage-Aware Topology Modeling and Adaptive Routing for Optical Satellite Networks	2026	Early Access	Sun Interrupters Joining processes	Optical satellite networks, supported by optical inter-satellite links (OISLs), provide reliable and low-latency optical connectivity. However, periodic and predictable sun outage events significantly compromise OISL availability, leading to frequent OISL interruptions and reduced network reliability. Existing routing algorithms often overlook the regularity of sun outage-induced interrupts and their differentiated impacts on services, resulting in degraded service performance. To address this challenge, this paper proposes a sun outage-enhanced time discretization OISL model and introduces a sun outage link-aware routing (SOLR) algorithm. By incorporating joint awareness of sun outage patterns and service requirements, SOLR employs an adaptive optimization mechanism to dynamically adjust routing decisions within temporal windows. Experimental results demonstrate that SOLR extends stable path durations by 39.9%, reduces interruption rates by 28.5%, and decreases blocking rates by 36.4%, significantly outperforming link-state-based routing algorithms. By effectively mitigating the impact of sun outages, SOLR ensures continuous optical service connections. This interruption-tolerant framework bridges network modeling and service provisioning, offering a robust solution for mission-critical service in optical satellite networks.	10.1109/TNSM.2026.3697856
Gergely Dobreff, Nóra Szlovencsák, Alija Pašić	A Framework for Disaster-Tolerant Slice Placement in Future Networks	2026	Early Access	Costing Costs Codes	Autonomous vehicles and telesurgery are placing increasing pressure on network operators to ensure that 5G and beyond networks can support a wide range of services with diverse and stringent requirements. Technologies such as Software-Defined Networking (SDN), Network Function Virtualization (NFV), and network slicing are key enablers for building an ecosystem capable of meeting these demanding conditions. Ensuring not only classical Quality of Service (QoS) metrics but also network resiliency is crucial, as failures in shared infrastructures can severely impact critical services. This paper addresses the problem of resilient network slice placement under arbitrary disasters or attacks, modeled as Shared Risk Link Group (SRLG) failure patterns. We propose an approach that guarantees strict end-to-end delay, bandwidth, and computing requirements while minimizing overall resource usage by accounting for potential failure scenarios. To this end, we introduce a Disaster-Tolerant Slice Placement Framework that enables network operators to define their own resilience scenarios and optimize the network accordingly. Several - routing and network coding–based - strategies are proposed and analyzed. We formulate the problem as an Integer Linear Program (ILP), analyze its computational complexity, and develop efficient heuristic algorithms to obtain near-optimal solutions. Extensive simulations demonstrate the effectiveness of the proposed methods in achieving resource-efficient and resilient network slice placement. The results show that high levels of resiliency can be achieved without excessive over-provisioning, positioning the proposed framework as an effective offline planning and benchmarking tool for 5G and beyond network design.	10.1109/TNSM.2026.3706661
Masoumeh Safkhani, Mohammad Reza Servati, Fatemeh Rezaei	HEIoT: A Novel Three-Factor Authentication Protocol for Enhanced Security in IoT and Next-Generation Networks	2026	Early Access	Authentication Internet of Things Protocols	The Internet has a significant impact on contemporary society, enabling a wide range of applications, including advanced cellular networks such as 4G, 5G, and 6G. Since these communications occur over shared or open channels, ensuring secure data exchange is of critical importance, as any weakness in the communication infrastructure may compromise system reliability. Device authentication in the Internet of Things (IoT) and user authentication in smart environments, such as smart homes, remain fundamental security challenges. As the first line of defense, authentication mechanisms must be robust, since vulnerabilities at this stage can expose the entire system to serious threats. To address these challenges, numerous authentication schemes based on cryptographic primitives, including Elliptic Curve Cryptography (ECC), have been proposed. In this paper, we present a comprehensive security analysis of an ECC-based three-factor authentication protocol proposed by Yuan et al. Our analysis shows that the protocol is vulnerable to desynchronization, user impersonation, traceability, and insider attacks, all of which succeed with probability 1 by exploiting at most two protocol phases. To mitigate these weaknesses, we propose an improved authentication scheme, called HEIoT. The proposed scheme is formally analyzed under the Real-or-Random (RoR) model to establish session-key security and is further verified using the Scyther tool. Moreover, a Python-based implementation is provided to demonstrate the practicality of the proposed protocol. Comparative results indicate that HEIoT achieves stronger security while maintaining acceptable communication, computational, and storage overhead.	10.1109/TNSM.2026.3702041
Wenying Wang, Mohammad S. Obaidat, Xuxun Liu, Kuei-Fang Hsiao	Node-Differentiated Resource Allocation for Media Access Control in Wireless Body Area Networks	2026	Early Access	Timing Resource management Media Access Control	Medium access control (MAC) is crucial for resource allocation in wireless body area networks (WBANs). However, existing MAC protocols often suffer from transmission conflicts and inefficient channel utilization. To address these issues, this paper proposes a Node-Differentiated Resource Scheduling (NDRS) MAC protocol, which dynamically allocates access resources based on node-specific requirements. This protocol employs a superframe structure consisting of a contention-based phase and a contention-free phase for data transmission. A Mamdani fuzzy inference system is utilized to calculate continuous node priorities. These priorities achieve fine-grained differentiation of node importance and thus serve as the foundation for transmission conflict minimization. During the contention-based phase, continuous and differentiated backoff times are assigned to nodes based on their priorities. These backoff times effectively reduce transmission collisions and enhance channel utilization. In the contention-free phase, time slots are preferentially allocated to nodes with higher priority, better channel utilization, and greater transmission reliability. This allocation thereby enhances channel usage efficiency and reduce transmission delays. This protocol is characterized by three key features: precise node prioritization, low transmission collisions, and high channel utilization. Extensive experimental results demonstrate that NDRS outperforms existing protocols in terms of average delay, throughput, packet loss ratio, and average energy consumption.	10.1109/TNSM.2026.3700262
Emilio Paolini, Andrea Pinto, Luca Valcarenghi, Flavio Esposito	Programmable In-Network Aggregation for Communication-Aware Federated Learning in 5G RANs	2026	Early Access	Modeling Timing Training	Federated Learning (FL) enables collaborative model training without sharing raw data, making it attractive for privacy-preserving applications at the wireless edge. However, when executed over real 5G networks, FL performance degrades due to uplink congestion, heterogeneous client capabilities, and intermittent connectivity. Most existing approaches attempt to mitigate these issues indirectly by optimizing clients (through adaptive participation, local training, or selection strategies) or by optimizing models (via pruning, quantization, or compression), but they ignore potential network bottlenecks. This paper introduces FLAG, an FL architecture that embeds innetwork aggregation directly into 5G gNodeBs, transforming the network into an active participant in the learning process. In particular, FLAG performs parameter aggregation at line rate within the 5G Service Data Adaptation Protocol layer and incorporates three mechanisms: Partial-Contribution Correction for loss-tolerant averaging, a timer-driven pipeline for real-time scheduling, and a deadline-based grouping strategy to mitigate stragglers. Experiments with realistic wireless emulation show that FLAG achieves up to 5.1× faster time-to-accuracy and maintains accuracy within 0.8% of a loss-free baseline, while reducing gNB-to-server bandwidth by aggregating pergNB rather than per-client. FLAG requires no modifications to clients or the parameter server, demonstrating how 5G-aware system design can make federated learning scalable, efficient, and resilient under real-world wireless conditions.	10.1109/TNSM.2026.3697723
Ishu Gupta, Ashutosh Kumar Singh	Statistical Analysis Driven Prediction Model for Malicious Entity Detection in Cloud Environment	2026	Early Access	Modeling Signal detection Clouds	Data sharing across distinct entities, including clouds, has become a necessity to enhance the performance of enterprises; however, it leads to data protection challenges. In this paper, a novel model aimed at data protection is presented when multiple untrusted parties are involved in the system. The proposed model enables secure data sharing and effective data distribution among the involved entities while minimizing the risk associated with data exposure. It enables the identification of malicious entities responsible for data leakage with high confidence. To this end, an efficient distribution strategy based on object and user selection, incorporating an operative access control mechanism, is proposed. Furthermore, algorithms are designed for the selection of data to be distributed among users. Experimental results demonstrate that the proposed model achieves significant improvements of 31%, 97%, and 64% in success rate, detection rate, and assessment rate, respectively, compared to prior works. Moreover, it reduces data leakage by up to 75% and lowers the error rate by up to 83% for malicious entity detection, while simultaneously enhancing detection performance and capability by up to 32% and 40%, respectively, over existing approaches.	10.1109/TNSM.2026.3704450
Ibirisol Fontes Ferreira, Cassio Vinicius Serafim Prazeres, Maycon Leone Maciel Peixoto, Eiji Oki, Gustavo Bittencourt Figueiredo	Narrow: A Fair Routing Multicast Algorithm for Distributed Interactive Applications in Edge Networks	2026	Early Access	Delays Algorithms Timing	Recent research in networking has increasingly focused on addressing the challenges of edge network services. A crucial issue in this context is routing, which must account for quality-of-service requirements. In particular, multicast routing provides optimized network services for groups of people using the same application, which is advantageous for operators and application providers. However, latency-constrained routing poses challenges when integrating diverse requirements into the routing computation, particularly when fairness among users is required. This work addresses the fairness requirement in multicast-overlaid and virtualized networks by presenting a solution that improves the equity of group interactions in the routing service. Our proposal, named Narrow, achieves fairer group interaction by selecting improved path options for multicast routing in edge networks. We compared Narrow with the Fair Shortest Path Tree (FSPT) and Chains algorithms from related studies on delay-constrained routing. Simulations indicated that Narrow reduced the inter-destination delay deviation by up to 84% and 49% relative to FSPT and Chains, respectively, across topologies of varying sizes. Similarly, Narrow improved by more than 99% against FSPT and by 70% against Chains across topologies with varying node degrees. Depending on the number of allowed alternative paths, Narrow reduced the inter-destination delay deviation by more than 99% compared with FSPT and by 38% compared with Chains. In emulated distributed interactive application session experiments, Narrow delivered the fairest response time, reducing it by 89% and 86% relative to FSPT and Chains, respectively. Furthermore, fairness in players’ scores improved by 20% and 16%, respectively, yielding more equitable group interaction from the application’s perspective.	10.1109/TNSM.2026.3704927
Huijuan Zhu, Chenhao Zheng, Zhongyuan Liu, Yuan Zhang	Reliable Interpretations of Deep Learning-based Malware Detectors via Deep Q-Networks	2026	Early Access	Malware Signal detection Modeling	Deep learning has become widely used in Android malware detection, but its black-box nature raises trust concerns, limiting its use in critical security areas. To address this, various interpretation methods have been proposed. Unfortunately, these solutions often suffer from inconsistent results and poor adaptability to model updates. In this work, we propose XDQNMal, a Deep Q-Networks (DQN)-based global interpretation framework designed to uncover the critical features that drive decisions in deep learning-based malware detectors. To enhance the reliability of interpretation, XDQNMal captures API call frequency features derived from the runtime behavior of each application (App). Then, it unites a DQN model with the TabPFN detection model to work collaboratively, using variations in detection results as reward signals. These signals guide the DQN model to gradually identify the most impactful features as interpretations for the detection model’s decisions. Our experimental evaluation on real-world datasets demonstrates that the proposed XDQNMal framework generates reliable interpretation for deep learning-based malware detection models. For instance, suppressing the critical features identified by XDQNMal leads to an average decrease of 20.30% in the probability that the malicious sample is predicted as malicious, highlighting the pivotal role these features play in the model’s decision-making.	10.1109/TNSM.2026.3699408
Jeffrey Redondo, Nauman Aslam, Juan Zhang, Zhenhui Yuan	Optimising QoS in HD Map Updates: Cross-Layer Multi-Agent with Multi-task and Mixed-Dependence (MTMD)	2026	Early Access	Optimization Timing High definition video	High-definition (HD) maps generated from autonomous vehicle (AV) sensor data are essential for enabling high levels of driving automation. However, offloading large volumes of raw sensory data to edge servers in dense vehicular ad hoc networks (VANETs) introduces significant latency due to network congestion and packet collisions. Existing solutions primarily focus on dynamically adjusting the minimum contention window (CWmin), while additional MAC-layer parameters — including the maximum contention window (CWmax) and interframe space number (IFSn) — remain largely underexplored. To address this, we propose a cross-layer multi-agent reinforcement learning (MARL) framework that jointly optimises CWmin–CWmax, IFSn, and transmission waiting time within IEEE 802.11p-compliant bounds. The proposed multi-task mixed-dependence (MTMD) framework decomposes the optimisation problem into specialised subtasks handled by selectively coupled agents, balancing coordination and scalability while avoiding the overhead of fully symmetric MARL or centralised hierarchical controllers. A lightweight orchestration layer coordinates agent interaction with the simulation environment via secure message exchange. Evaluated against standard EDCA and representative RL baselines, MTMD achieves latency reductions of 31%, 49%, 87.3%, and 64% for Voice, Video, HD Map, and Best-Effort traffic, respectively, confirming the effectiveness of structured multi-parameter optimisation for latency-critical vehicular applications.	10.1109/TNSM.2026.3705270
Huanlin Liu, Bing Ma, Yong Chen, Bo Liu, Haonan Chen, Jiachen Zou	Virtual Network Embedding Based on Hierarchical Reinforcement Learning for Admission Decision and Policy Fine-Tuning in Elastic Optical Network	2026	Early Access	Joining processes Elastic optical networks Algorithms	Network virtualization (NV) provides flexible services for diverse services by decoupling elastic optical network (EON) resources. Virtual optical network embedding aims to allocate the finite resources of EON to sequentially arriving virtual network requests (VNRs) with different resource demands. But existing methods have limitations, such as insufficient global optimization ability and a lack of awareness of link features. We propose a hierarchical reinforcement learning algorithm for admission decision and policy fine-tuning (HRL-ADPT), which achieves efficient virtual optical network embedding through a dual-layer collaborative optimization mechanism and a customized link-aware graph convolutional network (GCN) tailored for EON. The HRL framework decomposes the virtual network embedding process into two stages: 1) The upper-level agent generates admission decision and initial node embedding strategies based on topological and link features extracted by GCN, maximizing the revenue-cost ratio of individual VNR; 2) The lower-level agent dynamically fine-tunes the initial policy in combination with global resource load to optimize long-term resource utilization. The proximal policy optimization (PPO) algorithm is adopted as the basic training method. To address the sparse reward problem, the lower-level agent adopts a multi-objective intrinsic reward function, incorporating the revenue-cost ratio and load balancing to ensure local adjustments align with global objectives. Simulation experiments show that the proposed algorithm outperforms the compared NRM-VNE, MCTS-VNE, and HCMARL-VNE algorithms in terms of acceptance ratio, revenue-cost ratio, and spectrum utilization ratio.	10.1109/TNSM.2026.3706998
Yiyang Li, Wei Wang, Yibo Wang, Qiaojun Hu, Weiliang Zhang, Yongli Zhao, Xiaoyu Wang, Jie Zhang	Computing-State Driven Proactive Congestion Control for AI Cluster Interconnect Networks	2026	Early Access	Timing Modeling Fluid flow	The rapid upgrade of computing power and the prosperity of large language model (LLM) in data center networks (DCNs) lead to a rigorous demand for ultra-low latency and high throughput. To mitigate the overhead of collective communication during distributed training (DT), Remote Direct Memory Access (RDMA) has been widely adopted in DCNs. Particularly, congestion control algorithms (CCAs) designed for RDMA have attracted much attention to mitigate performance deterioration under network congestion. However, through comprehensive analysis, we investigate that, due to sluggish end-to-end reaction and slow rate convergence, existing widely used reactive CCAs have several limitations in handling bursty traffic (e.g., AllReduce). Specifically, excessive packets are transmitted before senders activate the reaction and converge to the fair rate, which builds up a deep queue and may incur subsequent significant throughput loss. In this paper, we propose a computing-state driven proactive congestion control (CSPCC) with easy deployability. CSPCC consists of the congestion prediction module and the active congestion response module. It leverages current computing state to predict network congestion time and inform corresponding sources in advance. We provide a detailed introduction to the implementation of CSPCC. Then, we conducted small-scale hardware tests and large-scale simulations to evaluate the performance of CSPCC. On our testbed, under NCCL-TESTs, CSPCC improves throughput by 1.67%–13.35% and decreases switch queue occupancy by 28.33%–58.33% compared to DCQCN. Furthermore, under concurrent multi-job LLaMA training, it reduces end-to-end job completion time (JCT) by 5.3%–9.0%.	10.1109/TNSM.2026.3705429
Ashiqur Rahaman Ridoy, Arnab Kumar Biswas	Adaptive Intrusion Detection Systems: Leveraging Meta-Learning for Improved Cybersecurity	2026	Early Access	Modeling Fluid flow Labeling	In the evolving landscape of cybersecurity, the integration of machine learning (ML) into Intrusion Detection Systems (IDS) has become critical for detecting both known and unknown attacks. This paper proposes a novel multi-stage hybrid IDS framework combining unsupervised anomaly detection, supervised classification, and low-shot adaptation for enhanced resilience to concept drift. The architecture comprises three interconnected stages: Stage 1 (unsupervised anomaly gating) and Stage 2 (supervised taxonomy learning) operate in parallel on a shared harmonized feature space; Stage 3 (Hybrid Low-Shot Adapter (H-LSA)) performs low-shot adaptation when the Stage 1 trigger fires, using transferred Stage 2 weights and a prototype-based cosine-kNN jury. Within the meta-learning family, we instantiate a metric-based low-shot adaptation approach eschewing second-order Model-Agnostic Meta-Learning (MAML) in favor of a partial-freeze, first-order protocol with a prototype-based cosine-kNN jury to enable rapid, low-resource adaptation. Extensive experiments were conducted on the CICIDS2017 (Source), CSECIC-IDS2018 (Target), and the modern BCCC-cPacket-Cloud-DDoS-2024 (Target) datasets (hereafter referred to as BCCC-2024). The results demonstrate that while static Stage 2 models suffer catastrophic failure under concept drift (dropping to 45.36% and 38.32% accuracy on CICIDS2018 and harmonized BCCC-2024, respectively), the proposed framework successfully adapts to new environments, achieving 90.64% accuracy on CICIDS2018 (Macro-F1: 0.8981) and 89.70% on BCCC-2024 (Macro-F1: 0.8801) with a low-resource support set of only 500 labeled samples per class. Furthermore, the system exhibits high computational efficiency, achieving a Stage 3 adapted inference latency between 0.0786 ms and 0.1667 ms per flow across diverse traffic profiles, proving its suitability for real-time, scalable deployment in modern cloud and edge network infrastructures.	10.1109/TNSM.2026.3706597
Hwejae Lee, Seonghoon Jeong, Huy Kang Kim	J1939DB-IDS: SAE J1939 Dual-Branch Intrusion Detection System against Novel Attacks	2026	Early Access	Modeling Controller area networks Transformers	The Society of Automotive Engineers J1939 (SAE J1939) protocol is widely adopted in commercial vehicles, extending the controller area network (CAN) with specialized message types and transport mechanisms. Despite its prevalence, security research for SAE J1939 remains insufficient compared to CAN. We address this gap by building three datasets that contain 11 realistic protocol-specific attack scenarios. We propose an unsupervised representation-learning-based intrusion detection system (IDS) utilizing a dual-branch autoencoder with few-shot threshold calibration. The model compresses categorical features through a 1D-convolutional neural network and continuous features through a Transformer encoder, reconstructing fused representations to detect anomalies through reconstruction loss. By leveraging SAE J1939-specific fields such as parameter group numbers (PGN) and source addresses, the system captures complex inter-signal relationships. On three datasets, our model achieves an average F1-score of 0.9871, consistently outperforming state-of-the-art methods. Benchmarks on an NVIDIA Jetson AGX Xavier confirm real-time feasibility. These results validate our protocol-aware feature strategy, offering a scalable and deployable IDS for commercial vehicle networks.	10.1109/TNSM.2026.3706666
Daishi Kondo, Yuya Shibuya, Rie S. Yamaguchi, Tomohiro Ishihara, Yuji Sekiya, Toshiyuki Nakata, Tohru Asami	Assessing the Adoption of Email Security Measures After Google’s New Sender Guidelines	2026	Early Access	Electronic mail Security Modeling	The email sender guidelines introduced by Google on October 3, 2023, mandate authentication protocols like Sender Policy Framework (SPF), DomainKeys Identified Mail (DKIM), and Domain-based Message Authentication, Reporting, and Conformance (DMARC) to enhance email security. However, how such platform-driven policies can effectively promote the adoption of security measures across the global email ecosystem remains unclear. In this measurement study, we analyze the impact of these guidelines by examining the adoption of email security measures across globally popular domains and country-specific subsets. Our results show that the adoption of SPF, DKIM, and DMARC has not yet achieved widespread uptake and exhibits significant regional disparities. In particular, domains associated with China, South Korea, and Japan exhibit consistently low adoption rates. While low adoption in China and South Korea can be partially explained by Gmail’s limited influence in these countries, Japan presents a striking contradiction, with low adoption persisting despite Google’s dominance. Focusing on Japanese-stock market-listed companies, we observe a significant increase in DMARC adoption following the introduction of the guidelines; however, a substantial proportion of entities remain non-compliant. These findings suggest that platform-driven policies alone are insufficient to achieve widespread security adoption and highlight the need for broader, ecosystem-level, multi-stakeholder initiatives.	10.1109/TNSM.2026.3707567
Soonbeom Kwon, Yusu Noh, Youngwoo Jang, Illyoung Choi, Byungchul Tak, In-geol Chun, Young-Kyoon Suh	Scalable and Robust Resource Provisioning via Adaptive Task Scheduling for Edge Devices	2026	Early Access	Schedules Scheduling Cloning	Edge devices, such as wearables, drones, and CCTV systems, are vital for real-time data collection in urban intelligence. However, their limited computational and storage capacities pose significant challenges. While offloading to public clouds offers scalability, it often incurs high latency and operational costs. Conversely, centralizing workloads on edge servers may result in the underutilization of high-performance edge devices. To address these limitations, we introduce ERPF, a Kubernetes-based Edge Resource Provisioning Framework that augments the capabilities of heterogeneous edge environments. ERPF orchestrates dynamic volume provisioning, GPU-aware resource allocation, execution context migration, and adaptive task distribution to improve system flexibility and efficiency. Building on this, we propose a novel adaptive task scheduling technique, termed eATS, composed of three key mechanisms: (i) Partition Smoothing Scheme for stable task granularity control, (ii) Resilient Edge Reintegration for failure detection and task reassignment, and (iii) Competitive Task Cloning for speculative execution with fastest-result commitment. The proposed eATS scheme reduces task execution time by up to 27.6%, lowers partition size variability by 8.7×, and improves scheduling robustness across heterogeneous edge devices over the baseline.	10.1109/TNSM.2026.3694238
Arash Heidari, Jamal N. Al-Karaki	NOVA: A Self-Supervised Graph Framework for Real-Time Anomaly Detection in Internet of Vehicles	2026	Early Access	Context Internet of Vehicles Modeling	The Internet of Vehicles (IoV) enables cooperative driving and real-time Vehicle-to-Everything (V2X) communication but remains vulnerable to behavioral and structural anomalies due to its dynamic, decentralized nature. Existing deep learning methods either overlook topological inconsistencies or ignore communication feature fidelity, while random-walk sampling introduces contextual noise. In this paper, we propose Network Observation for Vehicular Anomalies (NOVA), a self-supervised graph-based framework that detects both behavioral and structural anomalies in IoV networks without labeled data. NOVA models vehicular communications as attributed graphs and employs intimacy-guided subgraph sampling to extract meaningful neighborhoods. A Graph Convolutional Network (GCN)–based generative module reconstructs node attributes to reveal behavioral deviations, while a contrastive module validates structural coherence through embedding comparisons of real and perturbed contexts. Their hybrid anomaly score enables accurate, scalable, and real-time detection of compromised nodes. Performance results show that NOVA achieves state-of-the-art performance (98.7% accuracy, 98.1% F1), real-time throughput (~4.7k events/s at 5k msg/s), and strong robustness (AUROC 0.99, AUPRC 0.98, FAR 0.05) with near-linear scalability (≤40 ms latency for 50k vehicles). By integrating generative and contrastive self-supervised learning with context-aware sampling, NOVA significantly enhances IoV security, reliability, and adaptability.	10.1109/TNSM.2026.3696324
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
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
Heng Xu, Chengze Du, Zhiwei Yu, Letian Li, Ying Zhou, Bo Liu, Jialong Li	Distributed Flow Control for Efficient DNN Training Scheduling	2026	Early Access	Schedules Scheduling Training	Distributed Deep Neural Network (DNN) training generates periodic, long-lived, and interdependent flows that contrast sharply with the short, bursty, and independent flows typical of traditional cloud services. Existing flow scheduling methods, optimized for cloud traffic, struggle to handle the structured communication of DNN workloads, while static schedulers remain brittle under the computation jitter and stochasticity inherent in multi-tenant AI clusters. We propose a distributed traffic control and scheduling framework called PQ, which shifts from fragile global synchronization to a token-based queuing concept. PQ utilizes standard priority queues in commercial switches as elastic buffers, dynamically mapping task urgency to traffic priorities based on specific scheduling policies, such as minimizing waiting time, thereby accelerating efficiency. Results show that PQ achieves stable communication interleaving 3.6× to 8.8× faster than reactive baselines like MLTCP and FQ. Furthermore, it significantly optimizes performance by reducing average iteration time by up to 29.2% while maintaining higher link utilization.	10.1109/TNSM.2026.3704403
Dhiraj Bhattacharjee, Pablo G. Madoery, Abhishek Naik, Halim Yanikomerglu, Güneş Karabulut Kurt, Stéphane Martel	SQ-ROQ: A Scalable Framework for QoS-Aware Joint Routing and Queue Management in Satellite Mega-Constellations	2026	Early Access		The modern Internet accommodates a wide range of applications with heterogeneous quality of service (QoS) requirements across multiple network performance metrics. Low Earth orbit (LEO) satellite constellations have emerged as a promising solution to support these diverse services, not only in rural and remote areas but also in urban environments as a complement to terrestrial networks. Ensuring QoS compliance in such networks necessitates the joint optimization of routing and queue management, as effective traffic handling is critical to maintaining performance guarantees across multiple flows. In this paper, we formulate a joint routing and queue management problem in which QoS requirements are treated as soft constraints, with the objective of maximizing end-user experience while maintaining fairness among competing traffic flows. Given the combinatorial and NP-hard nature of the problem, we propose SQ-ROQ, a computationally efficient framework that decomposes the network into multiple domains and employs a Monte Carlo tree search (MCTS)-based optimization strategy to jointly determine routing and queue management decisions. Using the Starlink Phase 1 Version 2 constellation as a case study, we conduct a comparative analysis of end-user experience and fairness. The proposed algorithm shows higher and stable end-user experience and fairness served to multiple traffic flows as compared to the benchmarks. Building on this, we further investigate the inherent trade-off between optimizing user experience and ensuring fairness, as well as the impact of varying traffic loads on the proposed algorithm and the benchmark schemes. Finally, we demonstrate the scalability of SQ-ROQ through a comparative evaluation of both theoretical time complexity and measured average computation time.	10.1109/TNSM.2026.3705946