TNSM Searchable Index

Author(s)	Title	Year	Publication	Keywords
Muhammad Faizan Ayub, Xiong Li, Khalid Mahmood, Muhammad Asad Saleem, Salman Shamshad, Zahid Ghaffar, Yong Xie	A Lightweight and Secure Key Exchange Protocol for fortifying Home Area Network in Smart Grid	2026	Early Access	Protocols Smart grids Authentication	Smart grid networks rely on communication links to support monitoring and control of energy usage. Because these links are open, especially in Home Area Networks (HAN), security problems can occur. Devices may be physically captured, attackers may impersonate legitimate nodes, and temporary secret values may be exposed. Several key exchange protocols have been proposed to address these concerns. In practice, some of them still suffer from security weaknesses, while others introduce high communication and computation costs. In this work, we present a key exchange approach for HAN in smart grid systems based on Elliptic Curve Cryptography (ECC) and Physical Unclonable Functions (PUF). The protocol is analyzed using the Random-or-Real (RoR) model, along with an informal security discussion. Different attack scenarios, including impersonation, disclosure of stored meter data after capture, and ephemeral secret leakage, are considered. We also compare the proposed protocol with existing protocols and based on the comparison results, the proposed protocol shows a reduction of 3.843% in computational cost and 29.49% in communication cost.	10.1109/TNSM.2026.3746724
Qaisar Ali, Ihsan Ullah, Youn-Hee Han	Topology-Preserving Virtual Network Embedding Using Persistent Homology and Graph Attention Reinforcement Learning	2026	Early Access	Substrates Topology Joining processes	Virtual Network Embedding (VNE) maps virtual network requests (VNRs) onto shared substrate networks while satisfying node, link, and service constraints. Existing VNE methods mainly optimize resource-centric objectives such as CPU utilization, bandwidth consumption, acceptance ratio, and revenue, but often treat structural service patterns as implicit connectivity requirements. However, patterns such as redundancy loops, hierarchical aggregation, centralized control, and fault-tolerant structures may encode critical service logic, and their degradation can reduce reliability and violate service-level guarantees. This paper proposes TP-VNE, a topology-preserving and pattern-aware VNE framework that integrates persistent-homology-assisted structural characterization, graph attention-based representation learning, and proximal policy optimization. Persistent homology extracts multi-scale topological signatures from VNRs and substrate candidate regions, while complementary graph features distinguish acyclic structures such as stars and trees. A graph attention network learns topology-aware node embeddings by combining resource and structural features, and a PPO agent performs sequential node and link mapping under feasibility-aware action masking. Finally, a topology verification module validates the path-induced embedded subgraph before resource commitment. Simulation results show that TP-VNE improves the acceptance ratio from 48.5% to 83.5% at λarr = 0.20 and increases long-term average revenue from 2,780 to 4,980 compared with Baseline PPO, while achieving 89.3% pattern preservation accuracy with acceptable embedding overhead. Scalability experiments on GT-ITM substrates with up to 1000 nodes further demonstrate the robustness of TP-VNE under increasing network size.	10.1109/TNSM.2026.3744368
Stefano Servillo, Pietro Spadaccino, Marta Burocchi, Stavros Konstantaras, Flavio Luciani, Francesca Cuomo	AS-SETs Are Not Enough: From IRR Filtering Failures to Stateful Validation in IXP Route Servers	2026	Early Access	Filtering Filters Border Gateway Protocol	Internet Exchange Points (IXPs) provide critical infrastructure for Autonomous Systems (ASes) to interconnect and exchange traffic efficiently. To support scalable peering, IXPs use Route Servers (RSes), which allow ASes to exchange routes with multiple peers through a single Border Gateway Protocol (BGP) session. However, BGP’s implicit trust model exposes inter-domain routing to misconfigurations and threats. IXPs mitigate this through filtering techniques leveraging Resource Public Key Infrastructure (RPKI) and Internet Routing Registries (IRRs), which rely on AS-SET objects. However, improper AS-SET validation may lead to incorrect filtering of both invalid and valid announcements. In this paper, we characterize such vulnerabilities and show that they enable prefix hijacking through IXPs as well as the rejection of RPKI-valid announcements. Based on public internet data, we analyze AS-SET content quality, which could exacerbate both vulnerabilities. Moreover, we quantify them using one month of real-world routing data from the RSes of two European IXPs, NAMEX and AMS-IX, identifying 17,721 unauthorized announcements accepted and 294,112 RPKI-valid announcements rejected, and assess their presence across IXPs worldwide. Guided by these findings, we design a mitigation strategy consisting of a stateful validation pipeline that conditions IRR validation on RPKI and ASPA outcomes. We show how to implement it in practice through OpenBGPD, and we validate it in an emulated IXP topology.	10.1109/TNSM.2026.3745205
Tian-Yu Zuo, Xiuyi Zhao, Pan Li, Junxiong Lin, Mingyi Liu, Jiuchuan Jiang, Gengyu Lyu, Kai Di, Ning Luo	PrivKV-Sched: Budgeted Cross-Tenant KV-Cache Reuse for Multi-Tenant LLM Serving	2026	Early Access	Modeling Pricing Testing	Enterprise LLM services need faster responses and less repeated computation. Shared KV caches store computation results for reuse by later requests with matching input. However, content has different sharing permissions, and maximizing hits alone can permit reuse outside the authorized scope, creating privacy risks. Businesses that explicitly allow limited cross-user reuse also need to control its total amount. We propose PrivKV, which incorporates content permissions and reuse allowances into scheduling. For each request, it checks cached content and jointly selects a worker and reuse length based on saved computation, allowance consumption, and worker load. When spending is high, a dynamic price favors lower-cost reuse. An optional pre-execution check reserves the required allowance, preventing concurrent requests from spending the same balance twice. We compare methods with equal allowances on public request data and disable each control to examine its role. Tests cover different scales and inputs, small optimal solutions, and real GPU execution measuring service performance and scheduling overhead. Budget adjustment reduces unauthorized reuse, while pre-execution checks prevent overspending. With a common replacement rule, PrivKV retains about 96% of unconstrained cache hits. Real-model tests also verify the feasibility of pre-execution checks. For businesses allowing limited cross-user reuse, PrivKV applies content permissions and usage allowances to shared caches, limiting total unauthorized reuse while retaining computational savings.	10.1109/TNSM.2026.3745203
Qing Qian, Longwen Ran, Ruixue Tang, Huan Wang, Hongfa Ding, Yunhe Cui	SATEEN: A Heterogeneous Graph Neural Network for Saturation Attack Detection in SDN	2026	Early Access	Fluid flow Switches Modeling	SDN decouples the control plane from the data plane, enabling flexible network management. However, it is increasingly threatened by saturation attacks that target both switch flow tables and controller resources. Existing attack detection methods often focus on individual flows or network topology alone, neglecting the inherent interdependencies among flows and devices. This limitation can result in incomplete information aggregation and suboptimal detection performance. To address these challenges, we propose SATEEN, a GNN-based saturation attack detection method that leverages a heterogeneous Device-Flow Graph and a novel heterogeneous convolution model, HEGNN. The DevFlow-Graph explicitly models interactions among hosts, flows, and switches, incorporating multiple types of edges to capture structural and semantic relationships. HEGNN partitions the DevFlow-Graph into edge-type-specific subgraphs, computes attention-weighted aggregations within each subgraph, and integrates multi-layer information to generate expressive node embeddings for accurate attack classification. Experiments conducted on both FatTree and Agis topologies, using real-world background traffic, demonstrate that SATEEN significantly outperforms existing methods in detection accuracy and stability across different topologies and traffic patterns.	10.1109/TNSM.2026.3745553
Guan-Lin Chen, Yao Chiang, Hung-Yu Wei	Semantic-Aware Multi-LoRA Orchestration in Edge Federation: Hierarchical Multi-Timescale Optimization under QoE Constraints	2026	Early Access	Costing LoRa Dispatching	The rapid scaling of Large Language Models (LLMs) has driven the adoption of Multi-LoRA as a lightweight mechanism for model customization. However, deploying Multi-LoRA in edge federations introduces significant challenges in operational expenditure (OPEX) and latency efficiency. In this paper, we introduce a semantic-aware Multi-LoRA serving framework for edge federations that jointly optimizes OPEX and Quality of Experience (QoE). Specifically, we propose a semantic compatibility model based on behavioral embeddings to enable high-fidelity LoRA substitution, thereby reducing cold-start latency and redundant cross-region data transfers. We further develop a hierarchical multi-timescale architecture that separates long-term model provisioning from real-time request dispatching, allowing the system to adapt to dynamic workload skewness under data sovereignty constraints. Additionally, we design a Lyapunov-based dynamic dispatching algorithm to jointly optimize cross-cluster routing, node auto-scaling, and VRAM execution modes in real time. Extensive discrete-event simulations based on real-world Microsoft Azure Functions traces demonstrate that the proposed framework significantly mitigates the batch-squeezing effect and consistently outperforms state-of-the-art baselines in steady-state throughput, long-term OPEX reduction, and 95th-percentile Time-To-First-Token (TTFT) Service Level Objective (SLO) compliance.	10.1109/TNSM.2026.3747185
Tianle Lin, Lei Feng, Fanqin Zhou, Xudong Wang, Zhixiang Yang, Wenjing Li	Joint AP Selection and Power Allocation in Satellite–Terrestrial Cell-Free Network with Heterogeneous Multi-Agent Learning	2026	Early Access	Satellites Resource management Low earth orbit satellites	While Low Earth Orbit (LEO) satellites are vital for 6G non-terrestrial networks (NTN), applying Cell-Free Massive MIMO (CF-mMIMO) to high-mobility constellations remains challenging despite its capability to resolve conventional handover and interference issues. The traditional centralized processing model becomes impractical due to prohibitive latency, signaling overhead, and outdated Channel State Information (CSI), which degrades system performance. To overcome this challenge, we design a LEO Satellite Cell-Free Massive MIMO (LCF-mMIMO) system. In this system, each satellite independently determines its transmit power within the serving cluster, while statistical CSI is utilized to counter the fast-varying instantaneous CSI resulting from the rapid movement of LEO satellites. Additionally, to solve the minimum UE quality of service(QoS) maximization problem with reduced latency and signaling overhead, we develop a Heterogeneous Multi-Agent Proximal Policy Optimization (H-MAPPO) algorithm for joint Access Point (AP) selection and power allocation. In this algorithm, User Equipments (UEs) and satellites operate as heterogeneous agents: UEs perform AP selection based on local service demands, while satellites allocate power according to local power and interference states. Their decisions are coupled through the AP selection matrix, which converts UE-side access results into satellite-side associated UE sets and limits information exchange to selected UE-satellite associations. Simulation results demonstrate that the proposed scheme effectively adapts to dynamic LEO environments and achieves superior User QoS over learning-based benchmarks. Compared with the centralized SR-JCPA method, H-MAPPO maintains a comparable minimum QoS of 0.52 versus 0.53 under 16 UEs, while reducing the per-episode execution time from 17646.81 s to 96.81 s.	10.1109/TNSM.2026.3747765
Ramazan Enisoglu, Burak Alp Inan, Muhammed Ali Erbir	MSCANet: A Multi-Scale Channel Attention Network for Encrypted Traffic Classification	2026	Early Access	Encrypted traffic classification deep learning multi-scale convolution	Encrypted communication has rendered traditional traffic classification ineffective, creating challenges for QoS provisioning, network management, and security monitoring. Existing deep learning approaches exploit either spatial or sequence-level features in isolation, without jointly modeling multi-scale byte patterns and inter-packet ordering. We propose MSCANet, a hybrid architecture integrating a multi-scale 1D convolutional module, a sequentially applied Efficient Channel Attention (ECA) module, and a Transformer encoder, combining the two feature streams through a learnable weighted concatenation. With approximately 1.18M parameters, MSCANet attains 95.14% mean accuracy on the 20-class USTC-TFC2016 dataset and 92.61–98.01% across three 10-class sub-tasks over five random seeds, at a median per-sample inference latency of 1.29 ms on an NVIDIA RTX 5090 Laptop GPU. Against five baselines re-trained under an identical pipeline and schedule, spanning classical machine learning, CNN-only, attention-BiLSTM, and hybrid CNN–Transformer families, MSCANet is the most accurate on all four sub-tasks, improving over the strongest classical baseline by 6.16 pp and over the closest neural baseline by 2.38 pp while using 17.5% of its parameters and running 3.1× faster. These gains are demonstrated against the five re-trained baselines. Pretrained Transformers such as ET-BERT and YaTC report higher accuracy in their original publications, under their own preprocessing and with a pretraining stage that MSCANet does not use; the advantages we expect relative to them (no pretraining stage and, against ET-BERT, a model two orders of magnitude smaller) were not measured under our protocol, and we position MSCANet within the train-from-scratch regime.	10.1109/TNSM.2026.3748386
Aleksandar Avdalović, Joseph Khoury, Ibrahem AlJabea, Mustafa Hajij, Elias Bou-Harb	Beyond Flat Models: Preserving ICS Topology using Combinatorial Complexes for Hierarchy-Aware Intrusion Detection	2026	Early Access	Modeling Cells (biology) Integrated circuits	Industrial Control Systems (ICS) follow the Purdue model hierarchy, organizing sensors, actuators, Programmable Logic Controllers (PLCs), and supervisory control into distinct hierarchical layers. Despite this inherent structure, existing data-driven intrusion detectors still fail to model this intricate property. To address this gap, we introduce a Hierarchy-Aware Intrusion Detector, HAID, a topology-preserving framework that models an ICS as a Combinatorial Complex (CC), operating solely on process telemetry and trained on benign traces to detect falsified sensor measurements and unauthorized actuator commands. The complex captures devices, functional interactions, and PLC control zones within an ICS. CCs (unlike flat models) encode telemetry across hierarchical levels for training a Topological Neural Network (TNN). As such, HAID enables the embedding of the ICS Purdue model into the learning process, yielding anomaly scores and localization at each of the aforementioned levels. Evaluated on two water testbeds, SWaT and WADI, and on a simulated chemical process, TEP, HAID achieves competitive detection performance (82.7% F1 on SWaT and 50.1% on WADI, averaged over five runs), while providing explicit hierarchical localization unavailable in prior work. Through ablations, we confirm the added-value of hierarchical modeling, as removing the PLC-zone representation reduces F1 by 5.8 percentage points on SWaT and causes detection on WADI to collapse. The largest losses are on attacks that manipulate several devices at once, which device- and interactionlevel signals usually miss.	10.1109/TNSM.2026.3746967
Messaoud Ait-Yahia, Wael Jaafar, Rami Langar	Joint Design of Blockchain-Enabled Service Placement and Task Assignment in Vehicular Fog Computing Networks	2026	Early Access	Delays Timing Optimization	Driven by the evolution of blockchain and fog computing, vehicular networks are increasingly capable of supporting latency-sensitive applications with enhanced security and trust guarantees. However, the joint resource allocation for task offloading and blockchain services has been insufficiently investigated in existing works. To address this gap, this paper proposes a framework for jointly allocating resources of blockchain, users’ virtualized services, and Mobile Edge Computing (MEC) task assignment in Vehicular Fog Computing (VFC) networks. Specifically, we formulate the optimization problem as an integer nonlinear programming model aiming to maximize the satisfaction rate of users’ service requests while minimizing the corresponding blockchain operation time under mobility, queuing, instantiation, and resource constraints. To solve it in a timely manner, we design two-stage hierarchical low-complexity solutions, namely a Particle Swarm Optimization-based Joint Blockchain-enabled Service placement and Task Assignment algorithm (PSO-JBSTA), and a Genetic Algorithm-based approach (GA-JBSTA). Through extensive simulations, we demonstrate the effectiveness of PSO-JBSTA (resp. GA-JBSTA) and their adaptability to network conditions, achieving an average 35% (resp. 24%) improvement in users’ service satisfaction rate and 9.5% (resp. 10.2%) reduction in average blockchain validation delay compared with the baselines.	10.1109/TNSM.2026.3737068
Ting-Yu Chang, Cooper Cheng-Yuan Ku	Two-tier Framework with AutoML for Detection and Classification of Multiple Types of Anomalies in Intrusion Attacks	2026	Early Access	Modeling Optimization Probability	Ensuring cybersecurity is paramount for protecting sensitive data and defending against increasingly sophisticated cyberattacks. Consequently, intrusion detection (ID) has become a critical area of research in network security. This paper proposes a two-tier framework that leverages efficient automated machine learning (AutoML) techniques to address data imbalance and optimize feature combinations for ID and classification of multiple types of anomalies. In the first tier, two complementary models are selected: a primary model optimized for overall dataset performance and a secondary model specifically chosen for its effectiveness on balanced data distributions. In the second tier, a probability stacking approach, supported by Out-of-Fold (OOF) cross-validation, integrates insights from the first-tier models. It acts as a binary safety net that successfully recovers rare minority attacks while preventing irreversible information loss. The proposed framework effectively mitigates the adverse effects of data imbalance while requiring only a minimal runtime memory footprint of approximately 44 MB (NSL-KDD) and a total process footprint of 165.52 MB (CIC-IIoT-2025), and achieves a rapid cold-start initialization of 0.85 seconds. These advantages make it well-suited for edge computing. Experimental results on the NSL-KDD dataset demonstrate that the proposed approach achieves an overall accuracy of 99.73%, outperforming many state-of-the-art methods by 0.4-20.6%. Furthermore, evaluations on the CIC-IDS-2017 dataset show a 6.3% accuracy improvement and a significant 36% increase in macro-average recall compared with a random-forest-only (RF-only) model. Moreover, extensive validation on the contemporary CIC-IIoT-2025 dataset reveals a significant 4.20% improvement in Macro F1-score over up-to-date baselines. Finally, evaluations on an independent set with novel attack types (KDDTest+) confirm strong generalization capability, achieving 77.10% accuracy and underscoring the framework's robustness in modern industrial scenarios.	10.1109/TNSM.2026.3747311
Yakai Dai, Jia Chen, Xu Huang, Rui Dong, Tao Fu	VISTA: Verified Belief-Centric LLM Agents for Safe Network Management	2026	Early Access	Safety Writing Modeling	Large language model (LLM) agents now commit changes in production network management, where one change can touch routing-protocol state or a Kubernetes NetworkPolicy. The prevailing pipeline emits the change as a single text answer, so the network state, the competing root-cause hypotheses, and the operational invariants travel through the same token stream as the answer—a design that is unsafe on the NetArena dynamic benchmark: on capacity planning, the strongest supervised and retrieval-augmented baselines reach near-perfect correctness while leaving 41% of executed actions unsafe. VISTA gives each hidden quantity a persistent owner: it maintains a typed belief graph over topology and configuration, reasons over an explicit hypothesis trace, and routes every candidate write through a counterfactual verifier that emits a typed proof object, whose structured failure reasons re-enter the next round. On a shared Qwen2.5-Coder-7B backbone and NetArena’s official scorer, no single prompting strategy is safe across capacity planning’s ten query classes. Under π=WITHHOLD (proof failure blocks the write), VISTA reaches safety 1.000 at commit 0.869. Under π=FLAG (proof failure annotates but proceeds), it attains the per-class maximum on all ten classes, lifting safety from the 0.709 per-class oracle envelope to 0.869 at correctness 0.992, commit 1.000, and zero refusals, with a paired query-level margin of 153–0. An ablation attributes the gain: the gate itself does not move the safety rate, which is set by feeding belief and hypothesis structure back into generation, while the gate contributes a commit-time certificate agreeing with the official scorer on 869/869 admitted writes and a rejection whose structure decides repairability (60/86 versus 0/86), at ≈13× latency (3.520 s). On routing and Kubernetes the same workflow trades ≈70% refusal for high safety and is diagnostic, not deployable. Our implementation is released at https://github.com/dai-yakai/VISTA.	10.1109/TNSM.2026.3745152
Ashesh Gaur, Sridhar Radhakrishnan, Mohammed Atiquzzaman	Inverse Packet Classification: Reconstructing Behaviorally Equivalent Rule Sets from Observed Traffic	2026	Early Access	Merging Labeling Modeling	Network devices classify packets with ordered rule tables, but those tables are often inaccessible. Passive reconstruction can support behavior audits, misconfiguration analysis, and policy compliance without privileged device access. We define inverse packet classification as inferring a compact rule set from observed packet headers and device actions. The goal is observational equivalence on observed traffic, not recovery of the original configuration or priority order. The problem is difficult because traffic covers only part of the header space. Packet classifiers also use first-match semantics and structured prefix or interval predicates. We propose InversePC, which combines entropy-guided k-d-tree partitioning with greedy region merging. For a dominant default action, InversePC-HiB uses a hybrid split loss, exception-only merging, and a wildcard default rule. On synthetic classifiers, accuracy reaches 100% once coverage is sufficient. On native-resolution ClassBench filters, InversePC reaches 94.1% action agreement versus 88.3% for cross-validated CART on 1,000-rule sets. At 8-bit quantization, the two methods are statistically tied (98.1% versus 98.0%). In a well-covered 250-rule setting, InversePC uses 1.20× the original rule count versus 1.32× for CART. HiB is most useful for sparse, irregular default-permit ACLs, where it uses up to 2.5× fewer rules than InversePC at 99.8% accuracy. Optimized implementation makes native-resolution reconstruction practical in seconds.	10.1109/TNSM.2026.3744323
Ahlem Menaceur, Hamza Drid, Mohamed Rahouti, Yasmine Medjadba, Abdellah Chehri	Priority-Aware Dual-Queue Buffering for Reactive SDN Fault Management with Reduced Loss	2026	Early Access	Software defined networking Joining processes Loading	Software-Defined Networking (SDN) provides controller-driven flexibility for network and service management, yet reactive failure recovery often suffers from a recovery gap between fault detection and the installation of updated forwarding rules. Packets arriving during this interval are vulnerable to loss, while rerouted flows may overload specific links, undermining service continuity. To address these challenges, this paper proposes a dual-priority, queue-assisted reactive recovery mechanism that integrates traffic classification and buffering at the data plane. The design assigns flows to a high-priority queue (HPQ) or a low-priority queue (LPQ), ensuring that critical traffic is preserved while the controller completes rerouting. Evaluation on a 9-switch custom topology and the 16-node NSFNET backbone demonstrates that the proposed approach reduces packet loss (from 10.3% to 5.4% in the 9-switch topology and to below 1.9% in NSFNET) and improves post-failure load distribution, decreasing congested and surcharged links by 37.6% and 20.6%, respectively, compared to conventional reactive recovery. These results highlight that priority-aware buffering during the recovery gap enhances resilience, scalability, and operational efficiency for SDN fault and service management.	10.1109/TNSM.2026.3744288
Hongyuan Cheng, Lihua Yin, Tianqing Zhu, Hongyu Yang, Dexin Zhu, Weixiang Jiang, Nan Wei	Pattern2Bot: A malicious server IP detection model based on self-trained heterogeneous graph neural network	2026	Early Access	Labeling Modeling Signal detection	Botnets play a key role in network attacks such as Distributed Denial-of-Service (DDoS) attacks, spamming and click fraud. Command & Control server is an important node for botmaster to control bots and distribute attack commands. Bot disguise as normal domain requests through DNS traffic, but leave malicious records in DNS logs containing client IP, query domain, server IP and other complex interactions. This information provides important clues for detecting those botnets. In the current study, researchers detect botnets through multiple perspectives, including abstracting DNS communication records into graphs and using graph neural network models for detection. Conventional approaches often necessitate massive labeled datasets for model training, which substantially incurs training costs. Moreover, despite enriching node embeddings via topological relations, graph models often suffer performance degradation when confronted with structural semantic obfuscation from evasion techniques like double-flux. In order to understand the abstract and complex relationship patterns in DNS records while reducing label usage to lower training costs, we propose a botnet Command & Control server detection model based on DNS traffic. This is a self-training heterogeneous graph neural network model that does not require a large number of labels. By integrating the high-order relational semantics derived from multiple meta-paths with the local topologies of target nodes, the model achieves finer-grained structural awareness and semantic abstraction, thereby enhancing detection performance. We validate the effectiveness of the model in a real dataset, and the results show that the model has a better understanding of the special structure possessed by the IPs of Command & Control servers.	10.1109/TNSM.2026.3741111
Shyam Kumar Shrestha, Shiva Raj Pokhrel, Jonathan Kua	Adapting Large Language Models for TCP Fairness over Wi-Fi	2026	Early Access	Large language models TCP Modeling	Designing Transmission Control Protocol (TCP) Congestion Control Algorithms (CCAs) for heterogeneous Wi-Fi networks remains a challenge due to rapidly varying delay, loss, and contention dynamics. These effects often lead to CCA incompatibility, flow unfairness, and starvation among competing TCP flows. Although Deep Reinforcement Learning (DRL) has shown promise in mitigating these challenges, its slow convergence, high training costs, and limited generalization hinder practical deployments. In this paper, we propose TCP-LLM, a learning-augmented transport framework that leverages Large Language Models (LLMs) for compatibility-aware CCA selection. TCP-LLM encodes multivariate TCP time-series into token embeddings and performs single-step discrete CCA decisions through a lightweight LLM decision head. Parameter-efficient low-rank adaptation (LoRA) reduces the number of trainable parameters by approximately two orders of magnitude. Evaluation using traces collected from a physicalWi-Fi testbed with competing TCP Cubic, Bottleneck Bandwidth and Round-trip propagation time (BBR), and Performance-oriented Congestion Control (PCC) flows shows that TCP-LLM achieves the highest mean, geometric-mean, and minimum per-flow throughput among the evaluated schemes. TCP-LLM also exhibits faster and more stable training convergence and supports low-latency bounded inference. These results demonstrate the feasibility of LLM-based sequence adaptation for compatibility-aware transport-layer supervision under heterogeneous wireless conditions.	10.1109/TNSM.2026.3739364
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
Shuang Zheng, Xing Zhang, Michael Sheng, Haixu Wang, Wenbo Wang	Beam Hopping Low Earth Orbit Satellite Resource Allocation for Differentiated Services and Robustness Analysis under Model Attacks	2026	Early Access	Beams Satellites Resource management	Beam hopping (BH)-enabled Low Earth Orbit (LEO) satellites play a pivotal role in next-generation communication networks, providing global coverage, improving spectrum efficiency, and supporting flexible adaptation to heterogeneous service demands. To fully exploit these capabilities, artificial intelligence (AI) techniques are increasingly employed for dynamic resource allocation and power management. However, limited onboard resources and potential adversarial perturbations pose challenges to both efficiency and robustness. To address these issues, we leverage digital twin technology to accurately capture the spatio-temporal dynamics of user–satellite visibility, providing precise state information for decision-making. Building on this, we formulate a joint optimization framework for BH scheduling and power allocation as a Markov Decision Process and propose the BRIDGE—BH with Reinforcement learning incorporating Integrated Dirichlet and Gumbel-TopK Exploration—which integrates a quality of service (QoS)-driven subchannel scheduling mechanism to ensure efficient and differentiated resource allocation. The model’s robustness is systematically evaluated under three classical adversarial attacks. Simulation results demonstrate that our approach achieves superior energy efficiency, service throughput, and fairness, while the robustness analysis shows stable performance under the considered bounded adversarial perturbations.	10.1109/TNSM.2026.3710750
Franck Messaoudi, Luhan Wang, Abdelkader Mekrache, Adlen Ksentini, Bingxuan Li, Jialei Su, Sofiane Messaoudi, Salim El Ghalbzouri	The Brewing Storm in 5G’s Data Plane: Design and Evaluation of a High-Performance eBPF/XDP-Based User Plane Function	2026	Early Access	Quality of service Fluid flow Kernel	This paper presents the design and implementation of a novel 5G UPF leveraging eBPF technology to meet the stringent performance and programmability requirements of emerging 6G systems. Traditional UPF implementations often struggle to balance performance, flexibility, and resource efficiency-challenges particularly critical in CPU- and I/O-constrained edge environments. The proposed eBPF-based UPF architecture mitigates these limitations by embedding core functionalities, such as packet classification, forwarding, and QoS enforcement, directly within the Linux kernel via eBPF programs attached through XDP and tc hook points. Performance evaluation using TRex demonstrates that the proposed solution achieves competitive throughput, low packet loss, and efficient CPU utilization across traffic profiles. Moreover, it maintains full compliance with 5G Core Network standards. Comparative analysis with well-established open-source UPF implementations further underscores its advantages. This work highlights the potential of eBPF as a foundational technology for building next-generation, programmable UPFs optimized for edge cloud deployments in the 6G era.	10.1109/TNSM.2026.3720812
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