TNSM Searchable Index

Author(s)	Title	Year	Publication	Keywords
Michael Georgiades, Iacovos Ioannou, Hasan Islam, Ferheen Ayaz, Yun Hou, Kin-Hon Ho	Enhanced Vehicular Edge Offloading through SLA-Based Deep Reinforcement Learning and Risk-Aware Bandits	2026	Early Access	Service level agreements Modeling Timing	This paper investigates service-level agreement (SLA)-aware computation offloading in vehicular edge computing using two complementary online learners. SRM-FA-UCB combines staleness-aware transport exploration, contextual service-time prediction, empirical SLA screening, and selected-arm feedback. SLA-MA-PPO couples a state-dependent SLA action mask with a two-hidden-layer actor–critic, generalized advantage estimation, and cooperative KPI shaping. We evaluate both methods in an extended EdgeCloudSim environment with deterministic SUMO urban-grid mobility, V2X radio, congestion and handover effects, 200–1000 vehicles, and 10 paired replications per load. Among the six primary schemes, SRM-FA-UCB attains the lowest mean SLA violation, service time, and modeled energy with near-unity fairness. Additional controlled attribution with two simple screened heuristics and a screened FA-UCB control shows that the large improvement over conventional FA-UCB is primarily associated with the shared SLA-aware prediction and admissibility-screening stage; no independent endpoint advantage of the more complex post-screen SRM selector is established after Holm correction. SLA-MA-PPO significantly reduces SLA violations, mean service time, and modeled energy relative to PPO-GAE, while ablations identify action masking as its critical component. A controlled change-point experiment does not establish a transient benefit from the restless term. Code, configurations, seeds, and analysis scripts are provided through a public EdgeCloudSim research fork.	10.1109/TNSM.2026.3742669
Yingjie Hu, Weiping Wang, Shigeng Zhang, Hong Song, Ziheng Huang, Song Guo	Dual-State Representation Learning for Multi-Granularity IoT Device Identification	2026	Early Access	Internet of Things Modeling Training	The rapid growth of IoT devices has increased demand for traffic-based network asset management and security monitoring. Most existing methods operate in closed-set settings and may misclassify unseen devices as known models or return only an unknown label. To address this problem, this paper proposes a multi-granularity IoT device identification method based on dual-state representation learning. Device identity is modeled at three levels: type, manufacturer, and model, retaining type and manufacturer information when the device model cannot be reliably identified. The method extracts statistical, sequence, and raw-byte features and learns sequence and byte embeddings from idle and behavior traffic. Self-supervised learning and contrastive learning are used to improve the discriminative ability of representations. A state-aware gating mechanism then dynamically fuses the dual-state embeddings. Multi-task classification heads and confidence thresholds are used to support joint identification and rejection. Experiments on three public datasets show over 98% accuracy for known-device identification. The method also achieves over 97% accuracy for type and manufacturer prediction on the unknown-model test set and over 95% rejection rate for unknown models. Online deployment achieves an average latency of 3.1 ms and a throughput of 322 samples/s, demonstrating practical potential in open network environments.	10.1109/TNSM.2026.3738728
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
Shigen Shen, Muxi Li, Yizhou Shen, Jingnan Dong, Wenlong Ke, Ruilong Deng, Tian Wang	DeSPU: Privacy-Compliant Decentralized Sparse Personalized Federated Unlearning for Edge Intelligence-Enabled IoT Networks	2026	Early Access		Edge intelligence-enabled Internet of Things (Edge-IoT) increasingly relies on decentralized on-device learning to reduce cloud dependence and keep locally collected IoT data on terminal devices. However, deployed models may still memorize privacy-sensitive class-level knowledge and must support deletion requests after training. This paper studies class-level federated unlearning in a serverless Edge-IoT workflow where each IoT client maintains a sparse personalized IoT-local model and exchanges model information only with neighbors. We propose DeSPU, a decentralized sparse personalized federated unlearning framework under a practical deletion-window protocol. DeSPU estimates a target-class direction with a lightweight dual-model mechanism, applies semantic-layer adaptive linear unlearning to suppress target knowledge, and performs topology-aware local repair regularized by cached neighbor snapshots collected during routine peer-to-peer training. The online unlearning path does not store historical gradients and does not introduce additional post-request model communication beyond routine decentralized exchanges; the one-time β calibration scan is reported separately, and the calibrated β can be reused under the same configuration. To propagate deletion status beyond the requester, DeSPU also attaches a metadata-only forgetting flag to those routine exchanges and invalidates affected cached neighbor references at receiving clients. Experiments on CIFAR-10, MNIST, CIFAR-100, and CINIC-10 show near-zero target-class accuracy with high retained accuracy, up to ∼ 4.7 × 103 speedup over full retraining on CIFAR-10, and membership-inference ROC-AUC close to random guessing. Additional analyses over seeds, requester clients, target classes, cache staleness, sparsity, communication, and hardware cost further demonstrate the practicality and limitations of DeSPU for privacy-compliant Edge-IoT deployments. The project link is available at https: //github.com/aaaM2002/UN_CODE.	10.1109/TNSM.2026.3743397
Zheng Gao, Danfeng Sun, Kai Wang, Junjie Hu, Huifeng Wu	Dynamic Protocol and Service Negotiation via Device Dialogue for Resource-Constraint IoT Access	2026	Early Access		The rapid growth of the Internet of Things (IoT) has resulted in highly heterogeneous device environments, where diverse communication protocols and data formats coexist. Existing device access approaches mainly rely on static protocol configurations and predefined data interpretation mechanisms, causing redundant data acquisition and excessive resource consumption on resource-constrained edge nodes. To address these challenges, this paper proposes a Device Dialogue-based Protocol and Service Negotiation (DPSN) framework for resource-efficient IoT device access. DPSN first employs a lightweight dialogue mechanism to determine application-specific service requirements between devices and applications, thereby avoiding unnecessary data acquisition. Based on the negotiated services, a DRL-based adaptation mechanism is developed to dynamically select suitable protocol–interpreter combinations while minimizing edge resource consumption under latency and semantic quality constraints. The adaptation problem is formulated as a discrete decision-making process and solved by a Double Deep Q-Network (DDQN). Furthermore, a dynamic compilation strategy is designed to deploy only the selected protocol and interpreter modules, reducing unnecessary storage overhead at edge nodes. The proposed framework is implemented and evaluated in a mobile communication base station data acquisition scenario involving 1000 edge nodes. Experimental results demonstrate that DPSN satisfies service performance requirements while significantly reducing edge resource consumption compared with representative baseline methods, validating its effectiveness for large-scale and resource-constrained IoT deployments.	10.1109/TNSM.2026.3741850
Wang Qi, Pan Zhiwen, Liu Nan	A Hybrid Adaptive Two-step Broad Q-learning Network Based Outage Compensation and Recovery Scheme in Cellular Networks	2026	Early Access		As one of the important features of 6G, native artificial intelligence (AI) encourages deep integration of AI technology to establish a complete intelligent system. In this regard, network intelligent autonomy is a vital part, including the self-healing capability. Emphasis should be placed on the outage compensation and recovery in cellular networks, which is the focus of this paper. A two-step broad Q-learning network (TBQN) for parameter adjustment in fault compensation is proposed, where the broad learning system (BLS) accelerates the training process and the two-step structure addresses the difficulty of action selection in reinforcement learning with a large action space via rough adjustment followed by fine adjustment. What’s more, adaptive experience replay decreases the number of transitions to narrow the size of BLS and consequently, TBQN with the adaptive experience replay (ATBQN) can shorten response time and save computational expense. Besides, an algorithm devoted to the site plan of micro base stations (MBSs) is proposed, which works as an action and cooperates with ATBQN to realize the joint optimization of hybrid fault recovery methods. Simulation results show that for slightly faulty networks, the compensated coverage reaches nearly 95% without adding MBS, which surpasses other algorithms. For seriously faulty networks, the hybrid fault recovery strategy achieves 95% coverage with the minimum number of MBS while other MBS site planning schemes only offer lower than 90% coverage. Additionally, BQN saves 30% time compared with DQN with similar performance and with the assistance of adaptive experience replay, the time consumption further reduces.	10.1109/TNSM.2026.3740771
Shyam Kumar Shrestha, Shiva Raj Pokhrel, Jonathan Kua	Adapting Large Language Models for TCP Fairness over Wi-Fi	2026	Early Access		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
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
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
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
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
Mohammad Saberi, Ali Ahmadi Esfidi, Mahdi Dolati, Naeimeh Omidvar	FlexINA: In-Network Aggregation for Accelerating Distributed Machine Learning with Flexible Routing	2026	Early Access	Modeling Switches Timing	The growing scale and complexity of modern machine learning (ML) models have rendered distributed training indispensable. However, as model dimensions expand, communication overhead increasingly dominates the overall training time, creating a critical performance bottleneck. While techniques such as gradient compression offer partial relief, they often incur substantial computational overhead or require specialized hardware. In-network aggregation (INA) has emerged as a compelling alternative, offloading partial computations—such as gradient reduction—directly onto programmable network switches. Yet, current INA frameworks predominantly rely on rigid, static routing schemes or uncoordinated, opportunistic aggregation, fundamentally limiting their capacity to exploit the full potential of programmable data planes. To address this limitation, we formulate the Joint Scheduling-Routing for In-Network Aggregation (JINA) problem. JINA introduces a time-slotted execution model to enable fine-grained temporal scheduling synchronously with spatial routing. By leveraging source routing, it dictates perpacket forwarding paths while explicitly coordinating multi-hop partial aggregation across the network. Furthermore, we propose FlexINA, a scalable optimization framework that solves the JINA problem through a three-phase dimensionality reduction strategy: host-level pre-aggregation, topological switch filtration, and temporal window partitioning. Extensive evaluations across fifteen diverse network topologies demonstrate that FlexINA reduces the total network load by up to 8.3% compared to INA baselines, while maintaining high computational efficiency.	10.1109/TNSM.2026.3740503
João Gabriel Pazinato De Bittencourt, Fábio Gonçalves De Oliveira, Edson José Pacheco, Carlos Marcelo Pedroso	Packet-Level Causal Certification of Tail-Latency and Reliability Control in O-RAN Slicing	2026	Early Access	Radio access networks Regional area networks Context	An O-RAN slice controller holds two levers, the resource-block budget and the scheduling discipline, and reads an aggregate proxy that can pass a slice dropping packets or overrunning its latency bound. A lever that correlates with a key performance indicator need not control it. We answer, at the packet level, which lever an operator may act on. We evaluate compliance over every generated packet and lower-bound the probability that a lever both achieved compliance and was necessary for it. The bound carries information only when computed within each operating context and then standardized. The other order reduces to the average treatment effect, and the two coincide whenever the lever effect keeps its sign. A zero-sum allocation lever breaks that condition: the budget it grants one slice is taken from another. Over 3,720 runs one lever effect reverses from +0.32 to −0.66 with the neighbour’s load while averaging −0.008, so the pooled bound is zero and the stratified bound 0.156. Two contrasts on that lever, averaging −0.008 and 0.000, certify at 0.156 and at zero, which the pooled average effect cannot separate. The error guarantee covers false declarations of an effect, not the safety of acting on one.	10.1109/TNSM.2026.3740306
Tao Zhang	How to select blockchain applications for covert communication	2026	Early Access	Bitcoin Privacy Receivers	With characteristics like decentralization, transparency, anonymity and security, blockchain is an ideal platform for covert communication. How to select suitable blockchain platform is important to achieve secure and efficient covert communication with blockchain in practical scenarios. However, there is no systematical evaluation metrics currently. In the paper, we propose the first evaluation system with 10 key evaluation metrics from identity privacy, information stealthiness, robustness, performance and cost to systematically evaluate blockchain based covert communication schemes. Then different blockchain applications are compared with these metrics, comparative analysis shows that these blockchain applications have both advantages and disadvantages for covert communication. In the future, blockchain applications with improved privacy protection, lower latency and transaction fee can be explored in covert communication scenarios. Our work can lay the foundation and provide guidelines to assess blockchain based covert communication schemes and select blockchain applications suitable for covert communication.	10.1109/TNSM.2026.3742609
Yifan Zeng, Zihui Gu, Peijia Zheng, Huiyu Zhou	A Federated Semi-Supervised Framework for Data Efficiency and Privacy-Preserving Intrusion Detection in Internet of Things	2026	Early Access	Internet of Things Modeling Labeling	The Internet of Things (IoT) forms the foundation of modern smart environments, enabling intelligent industries, homes, cities, healthcare, and autonomous systems. However, as IoT devices increasingly connect to cloud platforms and the Internet, they become highly vulnerable to network intrusions that can lead to critical data breaches and service disruptions. This paper proposes a Contrastive Federated Semi-Supervised Learning Network Intrusion Detection framework (CFedSSL-NID), specifically tailored to enhance the security of IoT communications. It addresses practical scenarios where clients lack labeled data and computational resources, and where data privacy is paramount. The CFedSSL-NID framework enhances detection performance and robustness. It uniquely achieves this by synergistically leveraging abundant, unlabeled data from distributed IoT gateways through self-supervised contrastive learning, while optimally integrating supervised signals from a central server. This dual approach enables highly accurate intrusion detection while substantially mitigating the reliance on scarce and costly labeled data. Experiments on the TON-IoT, UNSW-NB15, and NSL-KDD datasets show that CFedSSL-NID outperforms federated and centralized baselines; additional evaluations under Non-IID data, asynchronous participation, and malicious-client updates confirm robustness, while communication and edge-inference analyses indicate its deployment feasibility.	10.1109/TNSM.2026.3742261
Mohammad Khosravi, Setareh Maghsudi	A Robust Optimization Approach for Regenerator Placement in Fault-Tolerant Networks Under Discrete Cost Uncertainty	2026	Early Access	IP networks Costing Costs	We focus on robust, survivable communication networks, where network links and nodes are affected by an uncertainty set. In this sense, any network links might fail. Besides, a signal can only travel a maximum distance before its quality falls below a certain threshold, necessitating its regeneration by regenerators installed at network nodes. In addition, the price of installing and maintaining regenerators belongs to a discrete uncertainty set. Robust optimization seeks a solution with guaranteed performance against all scenarios modeled in an uncertainty set. Thus, the problem is to find a subset of nodes with minimum cost for the placement of the regenerator, ensuring that all nodes can communicate even if a subset of network links fails. To solve the problem optimally, we propose two solution approaches, including one flow-based and one cut-based integer programming formulation, as well as their iterative exact method. Our theoretical and experimental results show the effectiveness of our methods.	10.1109/TNSM.2026.3740028
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
Chenxin Zhou, Cheng Huang, Qiang Zhang, Qiliang Xie, Zeqing Li	NESTTOR: Detecting Tor-over-Proxy Traffic with Factorized Decisions	2026	Early Access	Fluid flow Labeling Protocols	Tor users can place an encrypted proxy between the client and the Tor network to conceal the exposed entry connection. This additional layer also transforms the Tor byte stream through protocol framing, buffering, and TCP segmentation before an observer sees the outer client-to-proxy flow. The transformation breaks stable packet-to-cell alignment and raises two questions. We ask which Tor behaviors remain observable across different proxies and how a detector should combine the presence of an outer proxy with the presence of Tor traffic. Existing datasets primarily study Tor and proxy traffic as separate targets and provide limited support for answering these questions under a unified evaluation protocol. We propose NESTTOR, which trains a proxy gate and a proxy-conditioned Tor detector separately and combines their decisions with an AND rule. Its stage-based features capture relative connection evolution without reconstructing Tor cells. We construct a longitudinal benchmark of 349,891 bidirectional TCP flows that distinguishes Tor-over-Proxy (ToP), Pure Proxy, Direct Tor, and Ordinary traffic across four proxy protocols, 1,663 domains, and approximately 18 months. NESTTOR achieves 99.45% macro-F1 on confirmatory data from unseen domains and 88.50% on later captures.	10.1109/TNSM.2026.3743261
Ke He, Muhammad Rizwan Asghar, Jeong Do Yoo, Young Hun Lee, Hyunjae Kang, Huy Kang Kim, Dan Dongseong Kim	Liuer Mihou: A Practical Grey-box Adversarial Attack against Anomaly-based Network Intrusion Detection Systems	2026	Early Access	Modeling Signal detection Timing	Deep learning has gained popularity as a detection algorithm for Network-based Intrusion Detection Systems (NIDS) due to its expressiveness and speed. However, Deep learning algorithms are susceptible to adversarial attacks that introduce imperceptible changes to deceive the Deep learning algorithm into misclassifying the input. Existing adversarial attacks often overlook the practicality and replayability of the attack. In this paper, we present Liuer Mihou (LM), an adversarial attack designed to generate practical and replayable adversarial network packets, specifically targeting unsupervised anomaly-based NIDS deployed in Internet of Things (IoT) networks. The core concept behind LM is to leverage adversarial transferability and generate adversarial packets on a surrogate NIDS while considering predefined, semantic-preserving mutation operations to ensure practicality. To assess the effectiveness of LM, we objectively analyze its evasiveness against five general-purpose machine learning-based outlier detection algorithms (SOM, RRCF, LOF, OCSVM, and FROCC), as well as the state-of-the-art NIDS, Kitsune. Rather than claiming broad practicality, we characterize when and how packet-space attacks remain feasible: we quantify the trade-off between evasion and attack effectiveness, the distortion introduced by physical replay, and the conditions under which the attack transfers across detector families. We further show that LM’s mutation set is extensible beyond timing and size, adding TCP-window and payload-byte operators to evade a header-field-aware detector. Furthermore, we demonstrate that adversarial detectors such as Feature Squeezing and MagNet, as well as defenses designed for unsupervised anomaly detection, are largely ineffective in defending against LM. Moving beyond a theoretical setting, we conduct a replay of LM in two real IoT testbeds to analyze its practicality.	10.1109/TNSM.2026.3742885