Federated Learning (FL) enhances data privacy for End Equipment Workers (EWs) by enabling the sharing of model parameters instead of raw data. However, energy constraints and individual self-interest may discourage EWs from participating or slow down training, ultimately affecting the performance of the global FL model. To address these challenges, we propose a three-stage Stackelberg game-based framework that leverages wireless power to incentivize participation while ensuring the successful completion of FL tasks. In this framework, the Base Station (BS) publishes FL task and seeks to obtain an improved global model at a reduced cost. EWs train local models, aiming to maximize their payments while minimizing energy consumption. Meanwhile, the Charging Service Provider (CSP) supplies energy to EWs via Wireless Power Transfer (WPT) during model training and uploading, charging appropriate fees for the service. We employ the backward induction method to analyze the proposed game problem, proving the existence of a unique Stackelberg equilibrium and Nash equilibrium. Furthermore, we propose the Trust Region Method (TRM) to solve the unit payment strategy problem of BS. Extensive simulations validate that our method consistently outperforms benchmark schemes, achieving higher average utility across a wide range of scenarios.
Blockchain oracles are essential for enabling smart contracts to access and interact with off-chain data, where its security and trustworthiness are crucial for preserving the overall reliability and integrity of blockchain-based systems. However, existing reputation-based blockchain oracles are vulnerable to Sybil and collusion attacks. To address these issues, trusted execution environments (TEEs) have been leveraged to construct blockchain oracles. While these TEE-enabled oracles provide resistance against the above attacks, they typically depend on a centralized Root of Trust (RoT), which introduces risks such as root key pre-provision risks and single points of failure. Moreover, they often struggle to maintain trust over time, making them unsuitable for application scenarios that require long-term guaranteed trust. In this paper, we propose EnduraTrust, a highly secure blockchain oracle network empowered by a decentralized Root of Trust (DRoT), which can overcome single points of failure, offer trust sustainability, minimize the security risk of root key pre-provision, and provide essential participation incentive. Concretely, it adopts Physically Unclonable Functions (PUFs) to generate device-specific root keys, eliminating the risks associated with centralized key pre-provision. To confront mobile attacks and ensure sustained trust, it employs an off-chain process to generate attestation reports, which are then verified onchain through a non-interactive protocol. This protocol ensures robust integrity verification for Individual Root of Trust (IRoT) nodes while minimizing latency and overhead. In addition, we design a fair and secure IRoT node selection algorithm to form a trustworthy oracle committee to offer oracle services, protecting against Sybil and collusion attacks to which existing oracles are prone. Particularly, we apply an incentive mechanism to encourage oracle node participation and reliable behavior. We validate EnduraTrust through formal security analysis and performance evaluation based on prototype implementation. Our results show that EnduraTrust enhances root key security, realizes decentralization, offers fair oracle node selection, ensures sustained trust, exhibits strong robustness, and provides participation incentive. It surpasses existing decentralized attestation schemes in multiple dimensions, including security, contract execution efficiency, attestation protocol performance, and scalability. Besides, its performance regarding oracle response aggregation and aggregated response verification confirming its effectiveness.
We study a setting where an intelligent model (e.g., a pre-trained neural network) infers the real-time value of a target signal using data samples transmitted from a remote source. The transmission scheduler decides (i) the freshness of packets, (ii) their length (i.e., the number of samples they contain), and (iii) when they should be transmitted. The freshness is quantified using the Age of Information (AoI), and the inference quality for a given packet length is a general function of AoI. Previous works assumed i.i.d. transmission delays with immediate feedback or were restricted to the case where inference performance degrades as the input data ages. Our formulation, in addition to capturing non-monotone age dependence, also covers Markovian delay on both forward and feedback links. We model this as an infinite-horizon average-cost Semi-Markov Decision Process. We obtain a closed-form solution that decides on (i) and (iii) for any constant packet length. The solution for when to transmit is an index-based threshold policy, where the index function is expressed in terms of the delay state and AoI at the receiver. In contrast, the freshness of the selected packet is a function of only the delay state. We then separately optimize the value of the constant packet length. Moreover, we also develop an indexbased threshold policy for the time-variable packet length case, which allows a complexity reduction. In simulation results, we observe that our goal-oriented scheduler drops inference error down to one-sixth with respect to the age-based scheduling of unit-length packets.
In inter-datacenter (DC) elastic optical networks (EONs), dynamic service function chain (SFC) requests arrive and expire on-the-fly, posing significant challenges for efficient resource allocation. Existing heuristic and deep reinforcement learning (DRL)-based methods provide certain optimizations but rely on a full-connection-oriented provisioning scheme, which reserves the entire resource chain for the lifecycle of each SFC request, resulting in suboptimal resource utilization. To overcome these limitations, we propose a dynamic provisioning with store-and-forward scheme to address the dynamic SFC mapping and time scheduling problems based on DRL in inter-DC EONs. In this scheme, the virtual network functions (VNFs) and the light-path provisioning acquire resources only within their respective service times, which are realized by accurate time scheduling. To facilitate the decision-making process of the DRL agent, we decompose the intricate SFC request into several SFC sub-requests, solving them one by one in turn. Evaluations with two topologies demonstrate that our proposed DRL-based method can achieve blocking probability reductions of more than 10.1% and 13.8% when compared with the baselines.
For those seeking end-to-end private communication free from pervasive metadata tracking and censorship, the Tor network has been the de-facto choice in practice, despite its susceptibility to traffic analysis attacks. Recently, numerous metadata-private messaging proposals have emerged with the aim to surpass Tor in the messaging context by obscuring the relationships between any two messaging buddies, even against global and active attackers. However, most of these systems face an undesirable usability constraint: they require a metadata-private “dialing” phase to establish mutual agreement and timing or round coordination before initiating any regular chats among users. This phase is not only resource-intensive but also inflexible, limiting users’ ability to manage multiple concurrent conversations seamlessly. For stringent privacy requirement, the often-enforced traffic uniformity further exacerbated the limitations of this roadblock. In this paper, we introduce PingPong, a new end-to-end system for metadata-private messaging designed to overcome these limitations. Under the same traffic uniformity requirement, PingPong replaces the rigid “dial-before-converse” paradigm with a more flexible “notify-before-retrieval” workflow. This workflow incorporates a metadata-private notification subsystem, PING, and a metadata-private message store, PONG. Both PING and PONG leverage hardware-assisted secure enclaves for performance and operates through a series of customized oblivious algorithms, while meeting the uniformity requirements for metadata protection. By allowing users to switch between conversations on demand, PingPong achieves a level of usability akin to modern instant messaging systems, while also offering improved performance and bandwidth utilization for goodput We have built a prototype of PingPong with 32 8-core servers equipped with enclaves and conducted a case study on a real-world messaging metadata dataset to validate our claims.
As data centers continue to expand in size and complexity, obtaining global traffic insights necessitates aggregating statistical data from numerous individual nodes, a process critical for effective network management. However, in data centers, existing approaches often rely on querying individual endpoint hosts to gather cluster-wide statistics, which introduces substantial latency and reduces efficiency, particularly in large-scale deployments. To address this issue, we propose HiMon, a cost-efficient and high-accurate distributed monitoring system for optimizing traffic aggregation. HiMon enables distributed nodes to perform real-time, flow-level statistical processing and report the data to a manager node with minimal bandwidth consumption. The manager node aggregates the collected data to construct a comprehensive global traffic view. To enable high-speed and high-precision per-packet processing on child nodes, we introduce MaxSketch. MaxSketch's data structure and update strategy allow it to accurately estimate child node traffic with minimal memory and computational overhead. For high-speed aggregation on the manager node, we present PolySketch, which significantly boosts aggregation efficiency by delegating most computational tasks to the child nodes. Together, the hierarchical sketch structures of MaxSketch and PolySketch form the HiMon monitoring system. Experimental evaluations demonstrate that HiMon surpasses baseline algorithms, achieving a 17- $210\times $ improvement in traffic processing efficiency, a 25- $42\times $ reduction in manager node bandwidth consumption, and a 3.69- $8.97\times $ increase in accuracy.
Backscatter is promising to deliver near-zero-power communications for billions of ZigBee devices. However, existing backscatter tags face two practical challenges. Firstly, the deployment depends on dedicated excitors or additional receivers, driving up costs. Secondly, the modulator couples phase modulation with multiple high-frequency shifting clocks, boosting tag power. We propose BumbleBee, a pervasive, universal, and efficient ZigBee backscatter design. It reuses uncontrolled Bluetooth and proprietary FSK devices as excitors and demodulates with a single commodity receiver, slashing deployment cost. The key innovation of BumbleBee lies in overwrite modulation, which embeds tag data through dominant phase shifts, effectively overwriting ambient excitation content. The implementation of overwrite modulation depends on a novel Multi-Phase Shift (MPS) modulator that decouples baseband modulation from frequency shifting control, cutting clock requirements. These techniques benefit not only ZigBee but also other protocols that decode via the sign of phase shifts, as shown by a BLE5 backscatter extension. Our prototype uses commodity BLE4/FSK-based SDR excitors, an off-the-shelf FPGA, and commodity ZigBee/BLE5 receivers. Experiments show that BumbleBee achieves 223.2 kbps for ZigBee backscatter and 890.7 kbps for BLE5, 10x better than FreeRider, while MPS reduces power by 3.5x.
Blockchain interoperability and throughput scalability are two crucial problems that limit the wide adoption of blockchain applications. Payment channel networks (PCNs) provide a promising solution to the inherent scalability problem of blockchain technologies, allowing off-chain payments between senders and receivers via multi-hop payment paths. This paper presents a cross-chain PCN, called XHub, that extends PCNs to support multi-hop paths across multiple blockchains and resolves both interoperability and throughput scalability. XHub achieves service availability, transaction atomicity, and auditability. Users who correctly follow the protocols will succeed in making payments or get profits from doing the services. In addition, trustworthy information about hubs will be managed in a decentralized manner and available to all users. We conduct prototype implementation of machines that exchange Internet messages and run with two real blockchains as well as large-scale simulations based on real-world PCN topologies and transactions. The results show that XHub has small latency for cross-chain payments and can achieve a significantly higher success rate compared to the version without hub management protocols. This work is an important step towards the big picture of a decentralized transaction system that connects a wide scope of users in different blockchains.
Fault diagnosis is crucial for ensuring the reliability of interconnection networks. Traditional diagnostic models usually assume that edges connected to faulty nodes are fault-free, which is unrealistic in practice where both node and edge failures can occur simultaneously. The recently proposed HPMC* diagnostic model provides a more realistic framework by considering both node and edge failures simultaneously, but existing diagnostic approaches under this model have significant limitations in handling complex fault scenarios. This paper proposes HYBRID-GNN, the first graph neural network-based approach for hybrid fault diagnosis under the HPMC* model. HYBRID-GNN employs an edge-enhanced GraphSAGE with comprehensive feature engineering that extracts diagnostic characteristics from HPMC* syndrome data and enables joint training for node and edge fault prediction. HYBRID-GNN learns complex fault patterns from syndrome data, overcoming traditional diagnosability constraints. Experiments on multiple interconnection network topologies show that HYBRID-GNN matches the traditional algorithm in node fault diagnosis (achieving over 99% accuracy within the hybrid diagnosability bound), while delivering substantially higher performance in link fault diagnosis (with accuracy above 97%). Even beyond the diagnosability bound, HYBRID-GNN remains robust, maintaining over 98% node accuracy and over 83% link precision under high fault rates. Furthermore, results on real-world networks further validate its practical effectiveness, achieving over 99% node accuracy and over 95% link accuracy.
Controlled quantum teleportation (CQT) is a key technique that allows quantum information to be transmitted over a quantum network under the control of a network administrator/firewall. Existing CQT protocols rely on complex entanglement structures or increased number of qubits to enhance the administrator's ability to block unauthorized communication, referred to as the control level, which poses practical challenges on current quantum hardware due to decoherence and the fragility of quantum states. In contrast, we propose efficient single and dual controller protocols that improve the control level, while using practical and experimentally feasible entanglement resources such as GHZ and GHZ-like states. The proposed protocols adopt quantum hiding to enhance the network's control level, whether the receiver is compliant or non-compliant with the protocol. The dual-controller design further enables the integration of demilitarized zones (DMZs) into quantum networks, providing isolated intermediate regions jointly governed by two controllers and strengthening security boundaries. Our results demonstrate that the single-controller protocol achieves 87.5% control, reflecting a 75% improvement over the standard CQT scheme, while the dual-controller protocol achieves 98.44% control, corresponding to a 96.88% improvement. This improvement is achieved at a low cost of $2 - 9\%$ reduction in the rate of successful teleportation when tested in noisy environments. In addition, both protocols maintain high state-averaged teleportation fidelity across randomly generated input states. When benchmarked against existing protocols, the proposed schemes demonstrate superior performance by achieving the highest efficiency while using the least amount of quantum resources.
Network failure uncertainty and traffic demand uncertainty pose a series of challenges to efficiently solve network traffic engineering (TE) problems in the production wide-area networks (WANs). Prior works especially predict-then-optimize paradigm in TE systems encounter a significant mismatch between the upstream prediction task and the downstream optimization task, leading to potential demand loss risk and further degrading the performance of customer-facing applications in the cloud. In this paper, we present TUFTTE, a risk-driven TE optimization framework, where the objective function and constraints can be flexibly specified by the network operators. We employ a differentiable optimization layer to guide the prediction model with the objective of minimizing the network risks. When the network risk is defined as the demand loss, our approach can provably converge to the global optimum. Experimental results on real-world topology demonstrate that TUFTTE reduces the demand loss by 11.59% on average compared to the state-of-the- art algorithm. We believe that our paper deeply explores the potential of prediction and promotes the understanding on how to develop and deploy a general learning module into the commercial TE optimization.
Bandit with infinitely many arms (i.e., X-armed bandit) is an important variant of multi-armed stochastic bandits, which is useful to model different networking problems under both wired and wireless settings, e.g., online caching, dynamic channel/power allocation, rate adaption. However, the problem becomes challenging when the characteristic of the networking setting is affected by the side information (i.e., context) and distributed behavior. In this paper, we identify and study a novel problem, decentralized contextual X-armed bandit, where N agents collaboratively solve the problem within time span T. The problem is nontrivial because the infinite arms challenge and statistical information consensus issue make our setting go beyond a simple combination of X-armed bandits and multi-agent bandits. We develop a decentralized arm selection algorithm, called MACXUCB, by elaborating the contextual covering tree technique with a novel gossip communication protocol, which allows each agent to communicate efficiently with her neighbors. We prove that MACXUCB achieves a sublinear regret upper bound O- ( 1/D2dx +2dy +4 N (d)(x)+d(y)+1.5 / d(x) +d(y) +2 T-x(d)+d(y)+1/ d(x) +d(y) +2 )given aggregation period D, and the covering dimensions d(X) and d(Y) of arm and context spaces, which asymptomatically matches the lower bound Omega ((DN) (1/d)(x)+d(y)+2 T (d)(x) +d(y) +1 / d(x) +d(y) +2 up to a time-dependent factor. Moreover, MACXUCB enjoys a sublinear communication e complexity O-(NDT (0.5/(1-rho)) ) when tuning parameter rho is an element of (0, 1/2 ). Finally, we carry out experiments to verify the performance of our MACXUCB. The results show the effectiveness and efficiency of our MACXUCB.
Quantum federated learning (QFL) combines the robust data processing of quantum computing with the privacy-preserving features of federated learning (FL). However, in large-scale wireless networks, optimizing sum-rate is crucial for unlocking the true potential of QFL, facilitating effective model sharing and aggregation as devices compete for limited bandwidth amid dynamic channel conditions and fluctuating power resources. This paper studies a novel sum-rate maximization problem within a muti-channel QFL framework, specifically designed for non-orthogonal multiple access (NOMA)-based large-scale wireless networks. We develop a sum-rate maximization problem by jointly considering quantum device's channel selection and transmit power. Our formulated problem is a non-convex, mixed-integer nonlinear programming (MINLP) challenge that remains non-deterministic polynomial time (NP)-hard even with specified channel selection parameters. The complexity of the problem motivates us to create an effective iterative optimization approach that utilizes the sophisticated quantum approximate optimization algorithm (QAOA) to derive high-quality approximate solutions. Additionally, our study presents the first theoretical exploration of QFL convergence properties under full device participation, rigorously analyzing real-world scenarios with nonconvex loss functions, diverse data distributions, and the effects of quantum shot noise. Extensive simulation results indicate that our multi-channel NOMA-based QFL framework enhances model training and convergence behavior, surpassing conventional algorithms in terms of accuracy and loss. Moreover, our quantum-centric joint optimization approach achieves more than a 100% increase in sum-rate while ensuring rapid convergence, significantly outperforming the state-of-the-arts.
With the widespread deployment of 5G networks, efficient network optimization and planning have become increasingly important. The generation of mobile traffic and user data can help network operators understand and grasp the network’s operational status from different perspectives, enabling customized strategies such as wireless resource allocation and user access control. However, existing research primarily focuses on the generation of single-type data and lacks exploration of the interplay between mobile traffic and user data. Moreover, current generative models struggle to capture the spatio-temporal correlations between multimodal environmental data and mobile data. In this paper, we propose a Multimodal Context-aware Diffusion Model (MCDiff) for simultaneously generating mobile traffic and users. The model incorporates an interplay perception module to capture the correlation between mobile traffic and users. To better characterize the complex and dynamic features of urban environments, we innovatively propose extracting both spatial and temporal variations from multimodal contextual data and employing contrastive learning to align multimodal contextual features with mobile data. Extensive experiments on two real-world datasets demonstrate that MCDiff can accurately generate both mobile traffic and users, achieving up to a 23.11% improvement in fidelity metrics. Facilitated by our multimodal contextual fusion module, MCDiff exhibits strong controllable and generalization capabilities, with a minimal transfer gap of only 1.19%. Furthermore, by leveraging the generated mobile traffic and user data, we formulate network planning and optimization strategies. Experimental results highlight the superiority and practicality of our method.
Many proposals have demonstrated the efficiency advantages of software-defined networking (SDN) in managing data center networks. Common practices employ centralized traffic engineering (TE) in the SDN control plane to optimize load balancing and throughput. Meanwhile, for high availability purposes, the control plane is partitioned to ensure the impact of a single faulty controller is contained. However, the interaction between these two aspects is often overlooked. In particular, we show that the current control plane partitioning approach leads to imbalanced link loads and degraded application performance. To address this issue, we propose virtual slicing, a new control plane partitioning scheme. Virtual slicing achieves desirable traffic engineering performance while retaining the availability guarantees from the current approach. Virtual slicing is implemented and evaluated with real-world and synthetic traffic traces on production spine-free data center networks. Results show that virtual slicing reduces tail link utilizations by up to 28.4%, and improves flow completion times by up to 36%.
Federated learning (FL) is a widely studied framework for privacy-preserving collaborative training among multiple clients. However, real-world deployments reveal a persistent challenge: free-riders, i.e., participants who benefit from the system without contributing meaningful updates. If not properly addressed, free-riders can discourage honest contributors and ultimately impair both the fairness and efficiency of FL ecosystems. Existing defenses mainly rely on post-hoc per-client, per-round evaluation, leading to limited deterrence and high resource overhead, particularly in large-scale deployments. To tackle these problems, we propose FLET, a novel federated learning framework with test tasks. FLET introduces dedicated test tasks into the training process, blending them with real FL tasks while concealing their types from participants. These test tasks, generated from the reference datasets, serve as decoys that enable accurate detection of free-riding behavior. To enforce accountability, an economic penalty mechanism is employed, achieving both proactive (ex-ante) deterrence and reactive (expost) detection.We analyze the interactions between the server and participants through a free-riding suppression game model with asymmetric information (i.e., task type), and develop a strategic information disclosure scheme (i.e., revealing task requirements) to mislead attackers and proactively shape participant behavior. We characterize both pure-strategy and mixed-strategy perfect Bayesian Nash equilibria, and propose a lightweight strateg-ymaking algorithm that guides players toward equilibrium strategies under different conditions with modest overhead. Extensive experiments validate that FLET effectively suppresses free-riding and enhances the utility of both the server and participants. Our findings provide insights for designing cost-effective free-riding defenses in practical FL.
In-network aggregation (INA) has emerged as a key technology to alleviate communication bottlenecks in large-scale distributed training, but its performance is often hindered by suboptimal routing. Existing INA-aware routing algorithms suffer from certain limitations: they either lack a global, multi-job coordination mechanism, or operate on incomplete network models that ignore key hardware constraints such as switch processing capacity. These deficiencies lead to network congestion and inefficient resource utilization, ultimately undermining the full potential of INA. To address these challenges, we present INARouting, a novel framework that holistically solves the multi-job hierarchical aggregation routing problem. We propose TINA, a hierarchical aggregation protocol that supports multi-job in-network aggregation. To address different deployment scenarios, we develop two variants: INARouting-Opt that provides optimal solutions for moderate-scale networks, and INARouting-Relax, a fast and effective heuristic using LP-relaxation and a greedy score-based rounding algorithm for large-scale deployments. Through extensive experiments on various scales of Fat-Tree and Spine-Leaf topologies, we demonstrate that INARouting significantly outperforms state-of-the-art methods. INARouting-Opt achieves provably optimal solutions, reducing average job completion time by up to 56% compared to existing methods. Meanwhile, INARouting-Relax outperforms existing algorithms while being $5\times $ faster in solving time, enabling efficient routing in large-scale, dynamic environments.
In the cooperative multi-armed bandits problem, multiple agents cooperatively play the same multi-armed bandit game. The goal is to develop bandit algorithms with optimal group and individual regrets and low communication among agents. Despite extensive prior research, existing algorithms either cannot achieve time-independent communication costs or fail to achieve optimal individual regrets. We present a simple yet effective communication policy for cooperative bandits where the core algorithmic ideas fundamentally differ from prior work. That is, the proposed communication policy carefully determines the sharing frequency of agents’ local observations so that a certain quality of reward estimates is always maintained compared to a full cooperation policy. By deriving a separate lower bound on communication costs of cooperative algorithms, we show that our algorithms achieve the ultimate optimality goal: optimal group and individual regrets and time-independent communication costs.
Continuous crowdsensing in Mobile CrowdSensing (MCS) involves ongoing monitoring to gather real-time data over extended periods. A key challenge is determining appropriate intervals between consecutive data samplings to capture temporal variations, especially in unknown dynamic environments. Traditional Age-of-Information (AoI) driven methods maintain data freshness but can be costly and result in data redundancy. To address this, we integrate the AoI metric with information entropy difference to create a novel indicator, Composite Data Value (CDV), balancing data freshness and redundancy. Based on it, we investigate the online adaptive sampling problem for continuous crowdsensing in unknown dynamic environments. This problem is challenging due to the vast space of sensing strategies, difficulty in estimating rewards with unknown distributions and varying rates of change, and the degradation of optimal strategies as the environment evolves. Using a multi-armed bandit framework, we propose AdaScs, an online adaptive sampling optimization approach to maximize long-term CDV performance. First, AdaScs develops compact sensing strategies through limited trials. Then, it adaptively performs online sampling based on evolving reward estimations, identifying optimal strategies, detecting environmental drifts, updating strategies, and adjusting cycle lengths. Our results show that AdaScs outperforms all baselines, with accuracy increasing by 22.6% and reaction time at last improving by 54.6%.
Hierarchical Federated Learning (HFL) alleviates communication bottlenecks by organizing the system into multiple layers: client, intermediate aggregator, and server. Clients and aggregation layers form groups based on connection patterns, and the methods used for grouping and aggregation directly affect convergence performance. Currently, some studies have proposed grouping algorithms to address the non-independent and identically distributed (non-IID) characteristics of client data to improve performance. However, these methods do not account for network heterogeneity, such as clients using different quantization levels or adaptive quantization strategies to minimize communication overhead. Moreover, most methods rely on heuristics that blindly explore the combinatorial grouping space, incurring substantial computational overhead. In this paper, we conduct a rigorous convergence analysis and frame the dual challenges of heterogeneous data and quantization heterogeneity in HFL as the joint optimization of aggregation weights and grouping strategy. Specifically, we derive the optimal closed-form solution for the aggregation weights and propose an Alternating Optimization Hierarchical Optimal Weights (AO-HOW) algorithm to compute these weights. Building on this result, we propose DyGHFL-Dynamic Exclusion-Reallocation Grouping for Hierarchical Federated Learning, a structure-aware and efficient greedy algorithm that reorganizes groups by maximizing structured gain and updating weight coefficients according to current system conditions. Experiments on multiple datasets show that DyGHFL consistently outperforms existing baselines, demonstrating its effectiveness in HFL.
