TNSM Searchable Index

Author(s)	Title	Year	Publication	Keywords
Van-Linh Nguyen, Yared Abera Ergu	Adversarial Attacks on Hybrid Quantum-Classical Interference Classifier in Intelligent O-RAN	2026	Early Access	Modeling Interference Open RAN	Quantum machine learning (QML) is emerging as a key enabler of next-generation artificial intelligence (AI), offering more compact models and enhanced data processing capabilities. However, the integration of QML into AI-enabled network services can introduce new adversarial vulnerabilities, particularly the interface between classical encoders and quantum variational circuits. In this work, we investigate the susceptibility of QML-assisted signal classifiers to adversarial threats in the open radio access network (O-RAN) platforms. We introduce a new family of adversarial attacks, including a novel hybrid quantum-classical poisoning method (QC-Poison), along with hybrid gradient-based attacks (QC-FGSM and QC-PGD). QC-Poison induces long-term misclassification by injecting subtle adversarial, accumulating perturbations in the classical input space that propagate through the quantum encoder, effectively drifting the model’s decision boundary. Evaluation results show that QC-FGSM perturbs inputs based on the hybrid model’s gradients, reducing accuracy from 95.5% to 55.8%, while QC-PGD shows model’s performance reduction to 16.0% by iteratively corrupting quantum circuit parameters via loss maximization. QC-Poison achieves 23.9% accuracy under tight perturbation constraints without accessing training data or internal quantum parameters. The results expose critical blind spots in existing hybrid QML models that can be extended to AI-based features in the O-RAN core services. The study underscores the need for robust quantum-aware defenses that can mitigate stealthy adversarial attacks in distributed and QML-assisted applications in intelligent RAN.	10.1109/TNSM.2026.3717622
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
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
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
Madhura Adeppady, Yenchia Yu, Ali Rahmanian, Ahmed Ali-Eldin Hassan, Carla Fabiana Chiasserini	Efficient Management of Composite Heterogeneous Applications at the Network Edge	2026	Early Access	Central Processing Unit Servers Resource management	Edge computing is a promising paradigm for deploying latency-sensitive applications (Apps) as it brings resources closer to end users. Edge Apps often adopt a microservice (MS) architecture, breaking monolithic Apps into lightweight, containerized MSs that can be dynamically and independently deployed. However, managing such Apps involves three key challenges: (i) optimizing the placement of MSs to reduce both response time and resource overhead, (ii) handling MS migration or relocation as users move while minimizing App service disruption (App downtime), and (iii) enabling MS sharing across Apps while ensuring performance guarantees. We formulate this as an optimization problem, named Multi-microservice Application Placement (MAP), prove its NP-hardness, and introduce STEP (State and Topology-aware Edge-MS Placement), a polynomial-time heuristic. STEP distinguishes itself from prior work by: (i) jointly considering stateful and stateless MS characteristics in deployment decisions, (ii) exploiting MS shareability to reduce resource usage, (iii) balancing response latency, App downtime, and resource utilization, and (iv) leveraging multiple versions of the same MS to adapt quality of service to available edge resources. Our results in a small-scale scenario show that STEP achieves near-optimal performance with only 7% higher CPU cost than the optimal solution. Large-scale real-time experiments on a Kubernetes cluster demonstrate that STEP consistently outperforms competing methods, achieving up to 50% lower deployment costs while delivering 50% gain in app quality and saving 15% in radio resources with over 90% request success rates.	10.1109/TNSM.2026.3709656
Dev Gurung, Shiva Raj Pokhrel	LLM-QFL: Distilling Large Language Model for Quantum Federated Learning	2026	Early Access	Modeling Federated learning Large language models	As Quantum Federated Learning (QFL) scales toward distributed quantum networks, managing heterogeneous resources and communication bottlenecks becomes a critical challenge. This research proposes LLM-QFL, an adaptive network service management framework that leverages Large Language Models (LLMs) to optimize the operational efficiency of QFL systems. We introduce a federated distillation method in which locally fine-tuned LLMs serve as autonomous network agents. These agents adaptively manage service parameters by: i) dynamically adjusting local computation intensity (optimizer steps) based on loss gradients, ii) performing variance-aware client selection to minimize network-wide heterogeneity, and iii) implementing intelligent early stopping criteria to conserve bandwidth. By serving as an orchestration layer, LLM-QFL provides a synergy between LLMs and quantum networking. Our contributions include: i) Adaptive Performance and Efficiency: Reducing idle computation and significantly cutting communication overhead; ii) Theoretical Rigor: Convergence guarantees of O(1/T) for the adaptive management protocol; and iii) Scalable Deployment: Implementing PEFT (LoRA/QLoRA) for resource-constrained quantum service nodes.	10.1109/TNSM.2026.3712394
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
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
Xiaolan Ji, Biao Han, Yuedong Xu, Jinshu Su	ICCP: Towards Congestion Control Agent via Controlling Logic Decoupling and Algorithm Integration	2026	Early Access	Algorithms Fluid flow Modeling	To address the limitations of single congestion control algorithms (CCAs) in dynamic and heterogeneous network environments, selecting an appropriate algorithm from a pool of existing ones has become a widely adopted strategy. Existing mechanisms, however, are typically constrained by the Linux kernel’s unified abstractions, which limit the flexibility of selecting from a small set of in-kernel CCAs. Learning-based CCAs further increase the deployment cost because their inference logic is often compute-intensive and can block concurrent flows when executed within a synchronous control path. In this paper, we present ICCP, a unified congestion control framework that supports both heuristic and compute-intensive algorithms for concurrent flows. Rather than introducing a new reinforcement learning method, ICCP provides a three-layer, decoupled runtime framework consisting of the protocol stack, the user-space algorithm library, and the congestion control agent. ICCP uses asynchronous request handling, a shared proxy, and a “zero-copy” serialization-based RPC path to support both batch and single-inference modes with controlled communication overhead. We implement three distinct reinforcement learning-based congestion control algorithms within ICCP, including Sage, Orca, and DTCC, to evaluate the framework using representative compute-intensive CCAs. Simulations and real-world experiments demonstrate that ICCP maintains robust and efficient communication and inference performance as the number of concurrent flows increases. Overall, ICCP provides a practical runtime framework for integrating, evaluating, and deploying heterogeneous congestion control algorithms in multi-flow environments.	10.1109/TNSM.2026.3714992
Sanku Kumar Roy, Mohamed Samshad, Ketan Rajawat	UNet: A Generic and Reliable Multi-UAV Communication and Networking System Architecture for Heterogeneous Applications	2026	Early Access	Autonomous aerial vehicles Architecture Computer architecture	The rapid growth of UAV applications necessitates a robust communication and networking system architecture capable of addressing the diverse requirements of various applications concurrently, rather than relying on applicationspecific solutions. This paper proposes a generic and reliable multi-UAV communication and networking system architecture designed to support the varying demands of heterogeneous applications, including short-range and long-range communication, star and mesh topologies, different data rates, and multiple wireless standards. Our architecture is designed for both ad hoc and infrastructure networks, ensuring seamless connectivity throughout the network. Additionally, we present the design of a multi-protocol UAV gateway that enables interoperability among various communication protocols to enhance connectivity. Furthermore, we introduce a data processing and service layer framework with a graphical user interface of a ground control station that facilitates remote control and monitoring from any location at any time. We practically implemented the proposed architecture and evaluated its performance using different metrics, demonstrating its effectiveness.	10.1109/TNSM.2026.3715386
S A Harish, S Vignesh, Divya Pathak, Anil Kumar Sharma, Praveen Tammana	Anomaly Detection in In-Network Fast ReRoute Systems	2026	Early Access	Fluid flow Planing Delays	High-speed programmable data planes provide opportunities to implement data-driven fast reroute systems that quickly adapt to varying network conditions (e.g., congestion, failures) and improve network performance. The core of these systems has packet-processing algorithms running in the data plane that continuously look for traffic patterns (e.g., too many retransmissions) specific to a network condition (e.g., link failure) and take appropriate action (e.g., reroute). Despite their benefits, they also increase the potential attack surface. Adversaries can generate malicious traffic patterns resembling those anticipated by a fast reroute system and trick the system. Doing so would lead to poor network performance due to incorrect reroute decisions. In this paper, we propose a mechanism to detect whether the fast reroute systems are under the influence of malicious traffic patterns. Our key idea is to model the expected behavior using benign traffic features and use the model as a reference to determine whether the system is under the influence of adversaries. Using realistic attack traces, we demonstrate attacks on two fast reroute systems and successfully detect those attacks using the proposed detection mechanism.	10.1109/TNSM.2026.3715353
Abdullatif Albaseer, Elmahdi Bentafat, Mohamed Abdallah, Saif Al-Kuwari, Marwa Qaraqe	Incentive-Driven Honeypot Defense: A Multi-Agent DRL Framework for Securing Smart Grid Networks	2026	Early Access	Pricing Timing Learning (artificial intelligence)	Honeypot defenses present a robust solution for securing the Advanced Metering Infrastructure (AMI) against sophisticated cyberattacks. The efficacy of AMI defenses relies on the strategic deployment of honeypots by Small-scale Power Suppliers (SPSs) and the subsequent exchange of defense data with Traditional Power Retailers (TPRs). However, existing methods are limited by their requirement for prior information exchange and their inability to specify targeted services (i.e., protocols), making them impractical for dynamic environments. In addition, previous approaches have predominantly overlooked critical aspects such as service allocation and competition among SPSs. To address these challenges, we propose a novel Deep Reinforcement Learning (DRL)-based Stackelberg leader-follower game framework that facilitates tailored service allocation and fosters competition among SPSs. We leverage the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm, which combines centralized training and distributed execution, to enable each SPS to autonomously learn optimal strategies that consider defense data quality and attack rates, without requiring prior knowledge of deployment costs or the actions of other SPSs. This adaptability minimizes the overhead associated with information exchange and improves the defense of vulnerable services. In particular, our method operates by requiring data collection, as each SPS functions as an independent learning agent that generates its own training experiences. Extensive simulations demonstrate that our proposed DRL-driven approach significantly outperforms baseline methods in different performance metrics. It achieves higher utility for both SPSs and TPR while maintaining lower operational costs.	10.1109/TNSM.2026.3715400
Zening Li, Pin-Han Ho	Topology-Constrained Generative Modeling for Performance Monitoring and Structural Anomaly Definition in Optical Transport Networks	2026	Early Access	Windows Modeling Semantics	Electrical-layer performance monitoring (PM) in optical transport networks is reported as window-aggregated counters, under which propagation delay and signal regeneration boundaries are not directly observable. Consequently, different impairment mechanisms can lead to statistically similar PM trajectories, leaving PM-only methods without a principled notion of nominal behavior or anomaly detectability. To address this limitation, this paper proposes Topology-Constrained Partially Observed Dynamical System (TC-PODS). TC-PODS defines a topology-consistent nominal predictive reference directly in PM space by introducing a latent impairment state (LAT) that enforces service-path propagation and regeneration semantics as supervisory constraints, while explicitly modeling the irreversible projection induced by windowed PM observation. This formulation disambiguates nominal variability from anomalous behavior under partial observability and defines anomalies as PM trajectories that are incompatible with any topology-consistent nominal generation. By shifting PM analysis from algorithm-centric detection toward detectability-aware inference under the deployed observation protocol, TC-PODS provides a principled framework for forecasting and anomaly interpretation under partial observability, with future applications to structure-aware failure management.	10.1109/TNSM.2026.3715222
Wei Sai, Yihui Lu, Xin Guo	A Privacy-Preserving Security Framework for Multi-Party Data Fusion Computing Based on Homomorphic Encryption	2026	Early Access	Security Protocols Information rates	To prevent plaintext exposure in multi-party collaborative computing, this paper proposes a distributed secure multi-party computation protocol based on the Cheon-Kim-Kim-Song (CKKS) homomorphic encryption scheme. Data is encoded and encrypted at the source into CKKS complex polynomial ciphertext, enabling vectorized fusion under shared evaluation keys and threshold decryption in a decentralized architecture without a trusted central authority. Experiments on heterogeneous multi-institution datasets demonstrate low numerical error (9.0×10⁻⁷ at polynomial order 2¹⁶ and depth 12), effective scalability (throughput increasing from 1.12×10⁵ to 1.32×10⁵ ops/s and latency decreasing from 56 ms to 38 ms as nodes scale from 4 to 16), and strong robustness (70% decryption success at a 60% threshold and 95% recovery under malicious interference), showing that the framework achieves efficient computation with strict privacy protection for cross-party data fusion.	10.1109/TNSM.2026.3717343
Parisa Fard Moshiri, Xinyu Zhu, Poonam Lohan, Burak Kantarci, Emil Janulewicz	A Collaborative Edge Intelligence Framework for SFC Provisioning via Language Models	2026	Early Access	Modeling Large language models Retrieval augmented generation	As Software-Defined Networking (SDN) and Network Function Virtualization (NFV) enabled networks scale in size and complexity, monitoring and managing Service Function Chains (SFCs) under stringent latency and resource constraints becomes increasingly challenging. Although Deep Reinforcement Learning (DRL) is widely applied to SFC provisioning and Virtual Network Function (VNF) placement, enhanced network state monitoring is crucial to capture unexpected network conditions and guide DRL agents toward more adaptive decisions. In this context, Language Models (LMs) enable flexible, natural-language (NL)–based, query-driven network monitoring; however, directly processing complex multi-metric NL queries is computationally expensive and error-prone. This paper proposes an end-to-end (E2E) edge-based query translation pipeline that decomposes multi-metric NL queries into simpler single-metric sub-queries. Query decomposition is performed using a retrieval-augmented language model (RAG-LLM) and compared with a lightweight rule-based decomposition baseline. The resulting sub-queries are translated into Structured Query Language (SQL) using FLAN-T5. A cloud-only baseline, which directly translates NL queries to SQL without decomposition, is also evaluated. The results show that the rule-based edge pipeline achieves the lowest latency, reducing E2E latency by up to 78% compared to RAG-LLM and 18% compared to cloud execution under high work-loads. Under increasing arrival rates for the largest workload, the rule-based edge pipeline maintains superior performance over cloud, reducing total E2E latency by 57% at λ = 0.8. While RAG-LLM provides greater flexibility for unseen query patterns, both edge-based approaches achieve 100% NL2SQL accuracy with zero decomposition failures, outperforming the cloud-only baseline (95% accuracy).	10.1109/TNSM.2026.3717489
Katsumi Fujita, Hirofumi Noguchi, Masashi Kaneko	Power-Aware Uncore Frequency Scaling Based on Throughput Saturation	2026	Early Access	Frequency Central Processing Unit Information rates	Power-control mechanisms are essential for web-based processing applications to minimize energy consumption without causing excessive tail latency degradation. However, several challenges remain, including the coordinated control of core and uncore components and the cost of application modifications. Therefore, we propose a control framework for the uncore frequency alongside existing techniques for CPU core frequency scaling. This framework adjusts the uncore frequency on the basis of the server’s throughput state and does not require any application modifications. Evaluations of a web application show that, under the evaluated conditions, the proposed framework suppresses the extreme tail latency degradation and energy increases observed with techniques used for comparison. It also shows a more balanced trade-off between energy and latency.	10.1109/TNSM.2026.3716735
Liang Liu, Yejun He, Yujie Zhang, Siyuan Tan, Guiyan Liu, Hao Feng, Jie Duan, Songtao Guo	Multi-source Multicast SFCs Embedding in Space-Air-Ground Integrated Networks	2026	Early Access	Joining processes Delays Space-air-ground integrated networks	Space-air-ground integrated networks (SAGINs) offer seamless three-dimensional coverage and strengthened flexibility, which are recognized as a core network architecture of 6G. Software-defined networking (SDN) and network function virtualization (NFV) are two enabling technologies for SAGINs that can be utilized to sequentially arrange virtual network functions (VNFs) into service function chains (SFCs) to provide users with resource-efficient and delay-optimized multi-source multicast request (MMR) services. However, SAGINs exhibit significant dynamism and heterogeneity, it brings great challenges when dynamically deploying the MMR’s source nodes and SFCs for fulfilling MMR routing. This paper investigates the multi-source multicast SFC embedding problem (MMSEP) considering the determination of the source nodes for MMR, VNFs placement, as well as network resources and delay constraints in the SDN/NFV-enabled SAGIN. Firstly, we define and formulate the MMSEP and demonstrate its NP-hardness. Subsequently, we employ a heuristic algorithm to assign the optimal source nodes for all multicast destination nodes and utilize the markov decision process (MDP) to simulate dynamic transitions in network states. Finally, we propose a deep deterministic policy gradient with attention mechanism (DDPG-AM) to address the MMSEP, aiming to minimize resource consumption costs and delays while maximizing the revenue of the internet service provider. The simulation results demonstrate that the proposed algorithm surpasses the state-of-the-art DDPG algorithm by approximately 27% in network utility, 17% in latency reduction, and 5% in acceptance ratio.	10.1109/TNSM.2026.3717453
Ping He, Yu Yao, Xu Li, Yao Hu, Wei Yang	FIGAN: Diversity-Oriented Traffic Generation for Industrial Protocol Format Inference	2026	Early Access	Protocols Modeling Fuzzing	Protocol Format Inference is a pivotal step in the reverse engineering of proprietary protocols, yet its effectiveness is constrained by the scarcity of high-quality training data. In industrial control systems, the rigid and cyclical nature of traffic results in a "long-tail" distribution, where diverse functional scenarios are severely underrepresented. Existing generative approaches, primarily designed for fuzzing or intrusion detection, fail to resolve the intrinsic conflict between syntactic validity and semantic diversity required for protocol format inference. To bridge this gap, we propose FIGAN, a stage-wise decoupled generative framework tailored to synthesize high-fidelity traffic for protocol format inference. By isolating flexible distribution learning from rigid syntax enforcement, FIGAN liberates the generative process to extrapolate novel payload variations from a continuous latent space, effectively surmounting the limitations of sparse seed data. Specifically, the framework integrates three synergistic modules: first, heuristic pre-processing that constructs semantic templates as a prior knowledge base; second, a generative adversarial architecture optimized via discrete relaxation to explore high-dimensional payload patterns independently of syntax rules; and finally, a closed-loop verification mechanism that performs syntactic calibration and functional validation against simulated device responses. Evaluations on four real-world protocols (Modbus TCP, S7Comm, Omron FINS, and DNP3) demonstrate that FIGAN significantly outperforms state-of-the-art baselines. The source code has been open-sourced https://github.com/MissHP111/FIGAN.	10.1109/TNSM.2026.3717268
Doriana Monaco, Alessio Sacco, Flavio Esposito, Guido Marchetto	Adaptive SDN Autoscaling via Generalizable Multi-Agent Reinforcement Learning with EAGLE	2026	Early Access	Modeling Timing Training	Network automation and data-driven solutions are critical for modern network efficiency and resilience, especially as traditional manual management struggles to keep pace with increasing demands. The programmability of Software-Defined Networks (SDN) and their integration with Machine Learning (ML) algorithms have significantly advanced this quest, enabling data-driven network configuration. Within this context, autoscaling network resources is essential for efficiently operating softwarized and virtualized networks. However, current autoscaling solutions are limited by their logically centralized nature and their poor model portability across different network domains. To address these challenges, we propose EAGLE, a Multi-Agent Reinforcement Learning (MARL) system that autonomously orchestrates the scaling of network resources to meet flow demands and reduce power consumption. Powered by graph embedding, it generalizes to diverse network settings. We evaluate our solution over a Mininet-based emulator and assess its generalization capabilities on Fabric, a large-scale network testbed. Our results show that our approach can reduce flow completion time (FCT) by up to 40% while achieving up to 15% power savings. In addition, we show that our trained model can “zero-shot generalize” to unseen network topologies that share structural or statistical similarity with the training domain, hence reducing training time and associated energy costs.	10.1109/TNSM.2026.3717361
Enrico Boffetti, Arcangela Rago, Giuseppe Piro, Gennaro Boggia	Predictive QoE-Driven Radio Resource Management via Network Digital Twin in 5G and Beyond Networks	2026	Early Access	Quality of experience Resource management Synchronization	The evolution toward Beyond 5G networks introduces stringent requirements for intelligent Radio Resource Management (RRM) capable of jointly optimizing Quality of Experience (QoE) and resource utilization under highly dynamic conditions. This paper proposes a predictive QoE-driven RRM framework built upon an AI-enabled Network Digital Twin (NDT), which operates as a high-fidelity replica of the physical network to support proactive and efficient system-level resource allocation. The proposed approach integrates a Deep Learning (DL)-based module for forecasting future objective QoE metrics, namely Mean Opinion Score (MOS) values, with a Deep Reinforcement Learning (DRL) agent for dynamic Physical Resource Block (PRB) allocation. By incorporating predicted QoE levels over a finite horizon into the DRL agent’s state representation, the framework enables foresighted and policy-aware resource management while reducing synchronization overhead between the NDT and the physical infrastructure. Extensive simulations under heterogeneous traffic loads and QoE policies demonstrate that the proposed approach maintains high median QoE levels while adaptively regulating resource utilization, avoiding the systematic saturation observed with baseline static schedulers. The results further highlight stable learning behavior across DRL variants and confirm real-time feasibility with limited computational overhead.	10.1109/TNSM.2026.3716878