Last updated: 2026-11-21 05:01 UTC
All documents
Number of pages: 179
| Author(s) | Title | Year | Publication | Keywords | ||
|---|---|---|---|---|---|---|
| Wuzhao Li, Weian Guo | Switch-Coupled Scheduling for Energy-Bounded Heterogeneous Edge AI on Commodity Ethernet | 2026 | Early Access | Energy Modeling Joining processes Timing Poles and zeros Dispatching Windows Loading Scheduling Management edge AI energy-constrained scheduling Ethernet switching Lyapunov optimization serverless computing multi-tenancy | Heterogeneous edge-AI clusters behind commodity Ethernet must jointly manage compute queues, shared links, runtime residency, and energy budgets. We formulate request admission and assignment with per-hop FCFS resources, byte-limited TTL–LRU caches, temperature-dependent service, power uncertainty, deadlines, and tenant shares. Switch-Coupled Dual Scheduling (SCD) combines deadline feasibility, cost-aware energy credits, and device plus tenant virtual debts. Analysis establishes restricted-problem hardness, a state-correct finite-horizon certificate, and guarded commitment bounds. Nominal trace-driven simulations show higher offered on-time success and lower mean response than compute-first. These gains accompany higher task energy, admitted tail latency, and mean peak age of information. The success gain over matched drift-plus-penalty scheduling is incremental. Shared link state limits queue escalation under severe simulated bottlenecks. Elastic tenant allocation restores service under tight budgets while retaining device commitment bounds. Repeated hardware experiments compare scheduling under common resource constraints, execute trained neural and tree models on heterogeneous boards, and measure Ethernet path contention. The results support competitive deadline-oriented control with explicit service and energy trade-offs. | 10.1109/TNSM.2026.3752827 |
| 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 Modeling Optimization Schedules Scheduling Low earth orbit satellites Algorithms Bridges LEO satellite communications deep reinforcement learning digital twin resource allocation adversarial attack | 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 |
| Guangyu Zhang, Tong Ye, Ying Cui | Efficient Routing and No-Wait Scheduling for TSN: A Decomposable Formulation-based Method | 2026 | Early Access | Fluid flow Joining processes Algorithms Timing Scheduling Schedules Optimization Radio access networks Regional area networks Routing Time-sensitive networking time-triggered traffic routing and no-wait scheduling integer linear programming dual decomposition | Routing and no-wait scheduling (RnS) are crucial in managing time-triggered flows within time-sensitive networking (TSN). However, previous work formulated RnS optimization problems with logical constraints to portray frame conflicts, thus yielding algorithms that either incur long running times or exhibit low success rates in finding feasible points. To address this issue, this paper proposes a new integer linear programming (ILP) formulation, based on which we design an efficient and effective RnS method. In the proposed formulation, the occupation of a timeslot by a frame on a link is characterized by an indicator variable, and frame conflicts at a timeslot on a link are delineated by the sum of indicator variables. Our formulation contains fewer variables and constraints, and features a decomposition structure, based on which we develop a two-phase Optimization-Heuristic Hybrid (OHH) method. In phase 1, OHH applies a parallel iterative algorithm converging to optimal dual points. If phase 1 fails to produce a feasible point, phase 2 employs a lightweight greedy algorithm to find high-quality feasible points with a high success rate. Across 100 instances per topology with up to 500 flows, OHH yields running times comparable to those of prior heuristic algorithms, while achieving success rates and bandwidth consumption close to those of ILP solvers. | 10.1109/TNSM.2026.3755213 |
| Shengye Gong, Hui Yang, Qiuyan Yao, Xin Li, Tiankuo Yu, Wenxin Liu, Yang Zhao, Yucong Liu, Jie Zhang, Mohamed Cheriet | Resilient Hierarchical Polyhedron-based Configuration Protection for Large-Scale Multi-Domain Optical Networks | 2026 | Early Access | High performance computing Joining processes Protection Topology Costing Optical fiber networks Algorithms Modeling Architecture Computer architecture Network survivability multi-domain optical network network protection hierarchical polyhedron-based protection | Large-scale multi-domain optical networks are increasingly exposed to spatially correlated and concurrent failures, while monolithic pre-configured protection structures incur rapidly increasing global search complexity and protection-resource costs under heterogeneous physical constraints. To address this challenge, this paper proposes a resilient Hierarchical Polyhedron-based Configuration (HPC) architecture that decomposes a monolithic global survivability requirement into adaptive intra-domain connectivity constraints and a compact inter-domain connectivity constraint. To alleviate resource imbalance caused by topology-only network partitioning, a Topology-Resource Aware Domain Partitioning (TRADP) algorithm is developed to construct protection-supportable sub-domains by jointly considering topological structure and physical resource distribution. To avoid imposing a rigid protection level on heterogeneous domains, HPC assigns adaptive intra-domain connectivity targets according to local failure exposure and physical resource supportability. To reduce the complexity of cross-domain protection while preserving physical feasibility, a super-node abstraction and physical bridge-link mapping mechanism is employed to construct the inter-domain protection backbone under capacity, spectrum, and SRLG constraints. Extensive evaluations on networks of up to 1000 nodes and representative GEANT and NSFNET topologies demonstrate that HPC-TRADP maintains a recovery rate of 92.94% at 1000 nodes and 85.82% even when 30% of physical links fail concurrently. It further reduces protection overhead by up to 79.60% relative to p-KECS while maintaining efficient recovery paths, demonstrating a favorable balance between survivability, resource efficiency, and scalability. | 10.1109/TNSM.2026.3750417 |
| Xuejun Zhang, Hui Chen, Yexin Fan, Yanchun Hu, Jiami Guo, Xiaodong Yang | FedLoc-Guard: Cross-Round Behavior Modeling for Backdoor Defense in Federated RSSI Fingerprint Localization | 2026 | Early Access | Federated learning Modeling Location awareness Servers Received signal strength indicator Automatic speech recognition Fingerprint recognition Timing Educational institutions Cleaning Federated learning indoor localization Wi-Fi fingerprint localization backdoor attack cross-round behavior modeling robust aggregation | Federated learning provides a privacy-preserving paradigm for Wi-Fi RSSI fingerprint-based indoor localization, but remains vulnerable to stealthy backdoor attacks. In federated RSSI localization, environmental variation, device heterogeneity, and sampling-condition differences cause benign client updates to fluctuate across communication rounds, complicating malicious-update discrimination based on single-round statistics. To address this challenge, we propose FedLoc-Guard, a server-side defense framework that models client reliability from server-observable behavior across rounds. FedLoc-Guard estimates instantaneous reliability from directional consistency, relative update magnitude, and normalized turnaround-time consistency, updates client reliability across rounds, and uses the resulting reliability states for high-reliability client retention and risk-constrained aggregation with pre-normalization weight clipping. The method requires neither previously trusted clients nor an additional clean server-side reference set. Experiments on UJIIndoorLoc and Mall under IID and non-IID settings demonstrate that FedLoc-Guard substantially reduces attack success rates against BadNets, Scaling Attack, DBA, and an A3FL-inspired adaptive backdoor attack while maintaining useful localization performance under the evaluated settings, thereby improving the reliability and trustworthiness of federated indoor localization services. | 10.1109/TNSM.2026.3755818 |
| 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 Security MISO Array signal processing Vectors Satellites Reflection Interference Beamforming cascaded channels cognitive radio networks deep reinforcement learning dynamic hybrid reconfigurable intelligent surfaces energy harvesting poisoning attacks | 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 |
| Rahman Abdul Rafi, Christian Stephens, Shakil Ahmed, Ibrahim Almazyad, Ashfaq Khokhar | Asynchronous SLM Orchestrator for Mission-Critical Tactile Communications | 2026 | Early Access | Modeling Costing Optimization Delays Timing Labeling Jitter Architecture Computer architecture Radio frequency 6G+ Tactile Internet Mission Critical Systems URLLC SLM Cross-Layer Optimization | Mission-critical tactile applications such as remote surgery require sub-10 millisecond (ms) one-way latency and deadline-miss rates below 0.1% to preserve haptic stability, yet existing cross-layer optimization methods struggle to adapt transport, redundancy, and application parameters under wireless conditions without violating time constraints. To address this gap, we present SLM-COP, a two-tier edge architecture that decouples real-time execution from adaptive policy selection. A fast dataplane executor applies pre-validated cross-layer presets at 1–10 ms intervals while an asynchronous small language model (SLM) meta-controller runs every 50–200 ms to interpret telemetry and language-encoded objectives to propose configurations from 72 validated presets spanning FEC level, congestion control, frame aggregation, sampling rate, and packet-loss concealment. Using trace-driven experiments with da Vinci surgical kinematic traces from the JIGSAWS dataset across 5,000 emulated network conditions, the SLM meta-controller achieved mean cost 8.93 under Top-1 selection on 1,000 held-out scenarios, improving over rule-based heuristics by 53% while maintaining 100% feasibility with DMR ≤ 0.1%. Further, oracle analysis shows 85% of scenarios admit multiple near-optimal presets within a 10% cost margin. This facilitates Top-K shortlist evaluation, under which SLM-COP reaches cost 7.08 at Top-5 versus 6.74 for oracle. Batched inference over all 72 presets requires 100 ms, aligning with the slow-loop budget and preserving the fast-loop real-time guarantees. Thus, we demonstrate that asynchronous SLM-based orchestration can provide adaptive cross-layer control for deploy-able tactile internet systems over emerging 6G+ infrastructure. | 10.1109/TNSM.2026.3755916 |
| Qianli Di, Keju Du, Gang Chen, Hai Deng | ReAct-IDS: An Agentic LLM Zero-Day Screening Layer for UAV Intrusion Detection Cascades | 2026 | Early Access | Large language models Tools Poles and zeros Modeling Autonomous aerial vehicles Labeling Seeds (agriculture) LoRa Testing Training UAV Networks Intrusion Detection Systems Zero-day Attacks Agentic LLM ReAct Framework Explainable AI | Unmanned aerial vehicle (UAV) networks expose edge nodes to cyber threats. ReAct-IDS combines a local three-billion-parameter language model with tools and a supervised classifier. On UAVIDS/Cyber-Physical under leave-one-attack-out (LOAO), with the router bypassed, the post-hoc-selected four-tool/autoencoder-augmented cascades reach 63.3%/52.8% recall (run mean/three-seed sample-bootstrap mean) at false-unknown rates (FURs) 0.405/0.423 and known-class macro F1 0.684/0.605. FUR measures the fraction of known traffic flagged as unknown. Cyber-Physical headline recall covers only denial of service and replay, which share the benign capture schema. An equal-false-unknown-rate ablation gives an agent-minus-own-gate mean recall difference of −0.009 over four dataset–configuration combinations. Under IDS-Agent’s nine-attack CIC-IoT’ 23 protocol, mean unknown recall is 0.575 (95% confidence interval [0.560, 0.589]) at FUR 0.102, with detection supplied by the supervised confidence gate. An audit of 12,000 stored explanations against reconstructed reference evidence finds evidence-citing claims 97.7% supported yet claim-level faithfulness 0.44; on unknown verdicts it is 0.07. Incomplete original-prompt recovery limits this audit. | 10.1109/TNSM.2026.3755833 |
| Xiaolong Wang, Haipeng Yao, Wei Zhang, Tianle Mai, Hao Hao | Shared-Link-Aware Redundant Routing and CQF Flow Admission in Time-Sensitive Networks | 2026 | Early Access | Fluid flow Joining processes Schedules Timing Scheduling Optimization Modeling Routing Decoding Maintenance engineering Time-sensitive networking frame replication and elimination for reliability shared-link reliability redundant routing flow admission cyclic queuing and forwarding | Time-sensitive networking (TSN) requires deterministic latency and reliable delivery for industrial traffic. Frame replication and elimination for reliability (FRER) improves fault tolerance, but sparse topologies may force redundant routes to share links. The resulting overlap couples path failures with replicated cyclic queuing and forwarding (CQF) demand, making routing-layer reliability insufficient to ensure feasible admission and cycle allocation. We formulate joint redundant routing, weighted flow admission, and CQF resource allocation as a lexicographic optimization that maximizes admitted weight before minimizing resource use. Exact inclusion–exclusion evaluates shared-link reliability. Heuristic Optimization for Reliable Routing and Admission (HORRA) combines reliability- and deadline-feasible path-set libraries, a resource-aware CQF decoder, admission-gain-guided reordering, and bottleneck-guided destroy-and-repair. With a budget of 310 decoder evaluations, HORRA improves weighted admission by 1.7–3.3% relative to the one-shot baselines. Compared with the particle-swarm baseline, it reduces search time by 64.2% and 60.4% under moderate and severe contention, respectively. For identical admitted-flow sets, it reduces the resource objective by 11.65–16.84% relative to the two iterative baselines. The results demonstrate the benefit of coordinating shared-link reliability with CQF resource allocation. | 10.1109/TNSM.2026.3755712 |
| Zhuo Li, Yunlong Xi, Hao Xun, Yu Zhang, Teng Liang, Kaihua Liu | Flesh: A flexible hybrid packet classification scheme with high performance | 2026 | Early Access | Trees (botanical) Vegetation Ports (computers) Timing Algorithms Electronics packaging Software defined networking Construction Decision trees Elementary particles Packet classification Software Defined Networking Particle swarm optimization Hash table | Packet classification is widely used in network infrastructure and is a key technology supporting security and other functions. Real-time network services require classification schemes to have extremely high classification performance. Meanwhile, Software Defined Networking (SDN) enables more flexible rule changes, so the performance of rule updates in classification schemes has also gradually attracted attention. The schemes based on hash table have emerged due to their excellent update performance. Among these schemes, multiple tuples and chains need to be accessed during the classification to match rules. However, an excessive number of tuples can degrade classification performance. Additionally, overly long chains can also degrade classification performance. To this end, a flexible hybrid scheme called Flesh is proposed. Specifically, a partitioning algorithm based on the particle swarm optimization algorithm (PSO-Partition) is designed to reduce the number of tuples and initially suppress the generation of long chains. In addition, a hybrid storage structure (H-Storage) is designed to further shorten long chains. Experimental results show that compared with advanced schemes PT-Tree, LearningTuple, and HHM, Flesh achieved 1.60x, 1.07x, and 1.19x classification performance, as well as 1.88x, 1.52x, and 1.46x update performance, respectively. In addition, Flesh is scalable, which enables packet classification and rule updates for the 12-field rule set. | 10.1109/TNSM.2026.3755136 |
| Yuan Gao, Xuelong Wang, Zhenguo Dong, Yong Zhang, Yanyan Han | C2R: Causal-Corrected Residuals for Network Traffic Forecasting in Proactive Network Management | 2026 | Early Access | Modeling Forecasting Timing Learning (artificial intelligence) Fasteners Windows Foundation models Libraries Technology Telecommunication traffic Network Traffic Forecasting Time-Series Foundation Models Causal Discovery Residual Correction Network Management | In large-scale networks characterized by complex spatio-temporal couplings, accurate traffic forecasting serves as a cornerstone for proactive network management, capacity planning, and dynamic bandwidth allocation. Recent deep learning-based time-series foundation models have demonstrated remarkable capabilities in capturing long-term temporal dependencies for automated operations. However, a critical gap remains as these architectures often overlook network-specific topology in management scenarios and lack explicit modeling of cross-variable structural dependencies associated with traffic variations. These limitations can affect forecast accuracy during abrupt traffic changes. To address this challenge, we introduce C2R, a novel framework that augments the Chronos-Bolt foundation model with a TabPFN-based residual correction mechanism. Specifically, C2R constructs a regime-aware LPCMCI graph library by clustering historical traffic windows and learning lagged structural dependencies from the pooled observations within each regime, and then maps the selected structural candidates to residual errors to refine horizon-specific traffic forecasts. Experiments on core-network traffic datasets show that C2R achieves dataset-dependent incremental forecasting gains over the frozen backbone at the predefined evaluation origin while providing model-level structural attribution through the dependencies used by the residual-correction module. | 10.1109/TNSM.2026.3755281 |
| Yichen Zhang, Di Chen, Kaijie Zhu, Zekun Tao, Wei Lin, Rui Zheng | Beyond Valley-Free: Transformer-based AS Path Inference Using Path Embedding | 2026 | Early Access | Border Gateway Protocol Routing Ranking (statistics) Modeling Training Transformers Measurement Conferences Heart rate Probability AS path inference inter-domain routing Border Gateway Protocol network traffic analysis | Gaining insight into autonomous system (AS)-level paths is essential for understanding Internet routing behaviors and enhancing inter-domain routing security. Due to increasingly complex Internet topology and limited measurement access (e.g., router-side ICMP restrictions), few AS paths can be accurately observed, making AS path inference a necessity. However, most existing inference methods are developed based on the valley-free constraint. This limits their ability to capture real-world dynamic routing behaviors. In this paper, we propose PathRank, a Transformer-based method that infers AS paths from a source-AS to a destination-prefix through probability-based ranking, thereby closely reflecting real-world inter-domain routing complexities. From observable BGP data, PathRank generates candidate paths, encodes them as embeddings for a self-attention mechanism to capture cross-hop dependencies, and employs a prefix-length-weighted loss function during training to reflect real-world traffic impacts.We conduct experiments on large-scale public BGP datasets covering IPv4 and IPv6. PathRank places the observed BGP path among the top-10 ranked candidates in 96.82% (IPv4) and 96.65% (IPv6) of test cases, outperforming the strongest external baseline by 4.20 and 11.72 percentage points, respectively. On non-valley-free cases, where valley-free-constrained methods degrade significantly, PathRank maintains inference performance. | 10.1109/TNSM.2026.3752819 |
| Mayank Ramnani, Shasank Dixit, Sushil Yadav, Saad Ahmed, Sidharth Sharma | Split-Aware Function Placement with Availability Guarantees and Optical Provisioning in vRANs | 2026 | Early Access | Radio access networks 5G mobile communication Joining processes Topology Regional area networks Gallium Modeling Copper Optimization Costing 5G virtualized RAN VNF placement network slicing lightpath provisioning DWDM shared backup functional splitting genetic algorithm | The rapid evolution of beyond-5G and emerging 6G networks is driving the need for flexible, reliable, and cost-efficient virtualized Radio Access Network (vRAN) architectures capable of supporting heterogeneous services such as enhanced Mobile Broadband (eMBB), Ultra-Reliable Low-Latency Communication (URLLC), and Massive Machine-Type Communication (mMTC). Future disaggregated RAN systems are expected to rely heavily on network slicing, functional split flexibility, and optical x-haul infrastructures to support stringent performance, scalability, and availability requirements. In this paper, we present an integrated framework for reliable, slice-aware, and functional split-aware Virtual Network Function (VNF) placement with lightpath provisioning in disaggregated vRAN environments. The proposed approach maximizes mobile network operators’ profit by jointly optimizing function placement and optical resource allocation under latency, processing, bandwidth, and availability constraints. We formulate the problem as an Integer Linear Programming (ILP) model with two variants: one that employs unshared backups and another that uses a more cost-efficient shared backup scheme. To address ILP complexity, we develop a heuristic algorithm and a GA-based metaheuristic that provide computationally efficient alternatives for larger instances. Extensive evaluations on topologies up to 128 nodes show that shared backup variants yield up to 18% higher profit, while maintaining up to 5–10% lower normalized CPU usage than unshared counterparts. | 10.1109/TNSM.2026.3751852 |
| Jian Ye, Gaolei Fei, Jiajie Li, Xuemeng Zhai, Guangmin Hu, Ming Liang | Network topology inference via time-frequency consistency analysis of end-to-end traffic time series | 2026 | Early Access | Timing Topology Measurement Probes Frequency Modeling Trees (botanical) Vegetation Joining processes Tomography Network topology inference network tomography time-frequency consistency contrastive learning | In this paper, we study the classical network tomography problem of tree topology inference using end-to-end measurement. Traditional methods rely on time series correlations to measure shared path lengths. However, time-varying and non-stationary background traffic often biases these measurements. To overcome this, we comprehensively explore end-to-end traffic time series via time-frequency consistency analysis. Specifically, we jointly characterize time series in both time and frequency domains, imposing a consistency constraint. This ensures embeddings of the same time series across domains remain close in the latent space, providing a robust description of traffic dynamics. Our contrastive learning approach effectively highlights similarities among flows on common paths and distinguishes those on disjoint paths, thereby mitigating background traffic interference. Extensive evaluations across widely used probing strategies and metrics demonstrate that our embedding significantly enhances time series correlation and accurately measures shared paths. | 10.1109/TNSM.2026.3749558 |
| Byungchang Kim, Shinyoung Lue, Seonyeong Hwang, Youhee Park, Yeji Lee, Jaemin Jeong, Peter Bloodsworth, Euiseok Hwang | GRIDS: Generalized Representation-based Intrusion Detection System via Federated Contrastive Learning | 2026 | Early Access | Modeling Labeling Intrusion detection Training Federated learning Fluid flow Internet of Things Contrastive learning Artificial intelligence Signal detection Intrusion detection system federated learning contrastive learning anomaly detection network security transformer encoder | Existing AI-based intrusion detection systems are typically trained for specific network environments, leading to significant performance degradation when deployed in different settings or exposed to evolving attack strategies. We propose GRIDS (Generalized Representation-based Intrusion Detection System), a federated contrastive learning framework for cross-environment intrusion detection that keeps raw traffic data local. GRIDS employs a Transformer-based encoder trained with supervised contrastive learning across distributed network environments, learning a shared representation without exchanging sensitive traffic data. The encoder embeds network flow features into a latent space where semantically similar traffic patterns cluster together, enabling effective anomaly detection via k-nearest neighbor scoring. Evaluated on four heterogeneous NetFlow datasets, GRIDS outperforms existing federated IDS baselines on average with a single unified model. In leave-one-out cross-validation, a substantial portion of the detection capability of GRIDS transfers to network environments unseen during training, and the level of transfer varies across target networks. Deployment at such a network requires no labeled attack data or fine-tuning. It uses the benign traffic of the network as the kNN reference set and its unlabeled traffic for normalization and threshold calibration. The framework targets deployments in which a single model protects multiple heterogeneous networks. | 10.1109/TNSM.2026.3748922 |
| Junxiong Lin, Xiuyi Zhao, Pan Li, Tian-Yu Zuo, Mingyi Liu, Hailiang Zhao, Yichuan Jiang, Jiuchuan Jiang, Kai Di, Ning Luo | Hallucination-Aware Teaming for Reliable Service Composition in LLM-Driven Industrial Agent Networks | 2026 | Early Access | Modeling Large language models Educational institutions Costing Algorithms Conferences Collaboration Multi-agent systems Voting Social networking (online) LLM-driven industrial agent hallucination teaming reliable service composition multi-agent system | Large-language-model-driven (LLM-driven) industrial agents increasingly exchange intermediate results through service-composition pipelines, so an upstream hallucination can corrupt several downstream decisions. We formulate hallucination-aware teaming (HATP), which jointly considers capability coverage, distinct-base-family redundancy, resource budgets, and chain-level error propagation, and prove that its deterministic special case is NP-hard. We then propose HAT, a polynomial-time heuristic that combines master-driven recruitment with self-consistency, cross-agent agreement, external-constraint signals, and bounded fallback. In five simulator settings with 200 paired trials each, HAT has the highest mean Acc and lowest mean HPL in four settings; LLM Debate leads in Easy, and the HAT–Debate Acc differences in Easy and Complex are not significant after Holm correction. A 100-instance exact-enumeration study yields a 0.95% median relative utility gap and an approximately 10× median speedup for the tractable HATP instantiation with upstream discount and fallback disabled and a fixed scalar utility with normalized propagation length. Paired ablations show clear contributions from Phase B, bounded fallback, and the combined trust mechanism, whereas most individual trust-signal effects overlap with uncertainty. In a fixed 50-task live-LLM check using five 8B–30B model families, HAT attains Acc 0.280 versus 0.300 for Beta-Reputation and does not lead every comparator on propagation length. The live study is therefore a limited test outside the simulator and does not show that HAT is generally better in deployment. | 10.1109/TNSM.2026.3752977 |
| 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 Automated machine learning Labeling Training Algorithms Stacking Accuracy Tuning Intrusion Detection Anomaly Classification Cybersecurity Data Imbalance Computational Efficiency Two-tier Framework Machine Learning Probability Stacking Method | 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 |
| Arshee Naz, Sakshi Maurya, Karan Verma, Geeta Sikka | GRLDR: Space Debris-Aware Adaptive Routing for LEO Satellite Networks Using Graph Reinforcement Learning | 2026 | Early Access | Routing Satellites Low earth orbit satellites Modeling Joining processes Interrupters Timing Delays Learning (artificial intelligence) Space debris Graph Neural Network (GNN) Deep Reinforcement Learning (DRL) Space Debris LEO Satellite Network | The growing density of space debris in Low Earth Orbit (LEO) poses a serious challenge to the reliability of satellite communication networks. Existing LEO routing protocols primarily optimize hop count or latency, overlooking debris-induced risks that lead to frequent link disruptions. This paper proposes a Graph Reinforcement Learning-based Debris-Aware Adaptive Routing (GRLDR) framework that integrates Graph Neural Networks (GNNs) and Deep Reinforcement Learning (DRL) to enable intelligent, risk-aware routing in dynamic LEO satellite networks. Real satellite and debris orbital data from Space-Track.org are propagated using the SGP4 model to construct a debris-aware dynamic network graph. Debris risk is quantified using interruption time and radar cross-section features and categorized into low, medium, and high-risk levels. A Graph Attention Network extracts spatial and risk-aware features, while a DRL agent learns routing policies that jointly minimize debris risk, hop count, and end-to-end delay. Simulation results show that the proposed approach significantly reduces debris-exposed routing paths while maintaining low delay, achieving 98.8% hop optimality, up to 28% risk reduction, and a 100% routing success rate compared with conventional routing schemes. This work provides a scalable learning-driven solution for safe and resilient routing in LEO satellite networks. | 10.1109/TNSM.2026.3753808 |
| Edson José Pacheco, Mauro Sérgio Pereira Fonseca, Carlos Marcelo Pedroso | Interpretable Multi-Plane Intrusion Detection for 5G Networks with Adaptive Feature Engineering | 2026 | Early Access | Planing Modeling Recording Windows Modules (abstract algebra) 5G mobile communication Fluid flow Floods Timing Training Intrusion detection 5G security explainable machine learning cybersecurity feature engineering | Fifth-generation mobile networks expose multiple protocol planes to cyberattacks, yet intrusion detection research evaluates one feature representation, often on one plane, and relies on opaque classifiers that hinder root-cause analysis by network operators. We present an intrusion detection pipeline that applies one framework to every 5G network plane and trains an independent detector for each. The pipeline evaluates three feature modules (per-flow statistics, rolling temporal differentials, and windowed complexity descriptors) on each plane and selects one by a fixed rule under blocked and purged cross-validation, in which no training sample shares a record with a test sample. An Explainable Boosting Machine (EBM) classifies the traffic and produces auditable shape functions that reveal which traffic characteristics distinguish each attack class. Validation covers four public datasets, one of which contributes two planes, and spans user, mixed data, control, signaling, and service-based traffic. On these datasets, committing every plane to per-flow statistics, the module most common in the literature, costs 0.2493 F1 Macro on average and 0.6533 on NAS signaling. The EBM stays within 0.0058 F1 Macro of the best tree ensemble on every plane, and after Holm correction the cost of the additive restriction is not significant on any plane. On four planes, its mean F1 Macro is at or above that of six deep architectures. The service-based plane remains the hardest, at 0.5136 F1 Macro. These results indicate that interpretability and multi-plane coverage are achievable, and the pipeline accommodates further modules and planes as new attack surfaces emerge. | 10.1109/TNSM.2026.3755668 |
| Jie Song, Xiaoyu Luo, Pengyi Zhang, Chaopeng Guo | Cross-Tenant Benefit Policy Adaptation Without Authority Transfer in Live-Streaming Services | 2026 | Early Access | Authorization Labeling Management Recording Context Radio access networks Regional area networks Cleaning Modeling Filtering Cross-tenant policy adaptation authority-preserving service management policy reuse local governance warm-start initialization live streaming | Live-streaming services must adapt tenant-specific benefit policies as contexts change, but cross-tenant reuse must not transfer activation authority. We formulate adaptation under a tenant-local activation boundary and design a dual-plane lifecycle: a Global Coordination Service (GCS) aggregates eligible committed policies under a management-visible context label to initialize local search; tenant governance defines the revision region; the Channel Allocation Unit (CAU) projects, searches, and validates locally; stakeholders ratify the candidate; and the tenant commits the active version. Across 18 KuaiLive-grounded controlled context shifts, aggregate restricted mean time to recovery (RMST) is 28.60 cycles for Local, 11.20 for an authority-preserving Uniform Peer Average (UPA), and 8.20 for GCS. GCS reduces RMST over UPA by 3.00 cycles (95% CI [1.92, 4.28]). A 2 × 2 ablation attributes most clean and context-mismatch gains to robust filtering, while fitness weighting helps under fixed non-outlying contamination. With search-target bias 0.40, GCS retains 158/180 confirmed recoveries and RMST 15.20, versus 22.80 for UPA. These controlled results support faster governed adaptation in the evaluated setting. Authority non-transfer is a separate protocol property: GCS only initializes the tenant-local path, and activation still requires local authorization, validation, candidate-specific ratification, and commit. | 10.1109/TNSM.2026.3755260 |