网络与互联网架构

• 新提交
• 交叉列表
• 替换

查看 最近的 文章

显示 2025年08月06日， 星期三 新的列表

新提交 (展示 9 之 9 条目 )

[1] arXiv:2508.02960 [中文pdf, pdf, html, 其他]

标题： 一种用于动态无线接入网络中gNB移动性控制的强化学习框架 显示英文标题

标题： A Reinforcement Learning Framework for Mobility Control of gNBs in Dynamic Radio Access Networks

Pedro Duarte, André Coelho, Manuel Ricardo

主题： 网络与互联网架构 (cs.NI)

无线环境的复杂性不断增加，其特点是用户移动性和动态障碍物，这给保持视线（LoS）连接带来了挑战。移动基站（gNBs）通过物理移动来恢复或维持LoS，成为一种有前景的解决方案，从而需要开发智能算法来进行自主移动控制。作为CONVERGE研究项目的一部分，该项目正在开发一个实验舱，将计算机视觉（CV）集成到移动网络中，并在动态无线环境中提高服务质量（QoS），本文提出了两个关键贡献。首先，我们介绍了CONVERGE实验舱模拟器（CC-SIM），这是一个用于开发、训练和验证移动gNB移动控制算法的3D仿真环境。CC-SIM模拟用户和障碍物的移动性、视觉遮挡和射频（RF）传播行为。它通过OpenAirInterface（OAI）射频模拟器与独立的5G系统紧密集成，支持离线强化学习和实时测试，从而在真实的网络条件下进行验证。其次，利用CC-SIM，我们开发了一个深度Q网络（DQN）代理，该代理能够主动重新定位gNB以应对动态环境变化。在三个代表性用例中的实验表明，与静态部署相比，训练好的代理显著减少了LoS阻塞时间——最多减少42%。这些结果突显了基于学习的移动控制在自适应下一代无线网络中的有效性。 显示英文摘要

The increasing complexity of wireless environments, characterized by user mobility and dynamic obstructions, poses challenges for the maintenance of Line-of-Sight (LoS) connectivity. Mobile base stations (gNBs) stand as a promising solution by physically relocating to restore or sustain LoS, thereby necessitating the development of intelligent algorithms for autonomous movement control. As part of the CONVERGE research project, which is developing an experimental chamber to integrate computer vision (CV) into mobile networks and enhance Quality of Service (QoS) in dynamic wireless environments, this paper presents two key contributions. First, we introduce the CONVERGE Chamber Simulator (CC-SIM), a 3D simulation environment for developing, training, and validating mobility control algorithms for mobile gNBs. CC-SIM models user and obstacle mobility, visual occlusion, and Radio Frequency (RF) propagation behavior. It supports both offline reinforcement learning and real-time testing through tight integration with a standalone 5G system via the OpenAirInterface (OAI) RF simulator, enabling validation under realistic network conditions. Second, leveraging CC-SIM, we develop a Deep Q-Network (DQN) agent that learns to reposition the gNB proactively in response to dynamic environmental changes. Experiments across three representative use cases show that the trained agent significantly reduces LoS blockage time - by up to 42% - when compared to static deployments. These results highlight the effectiveness of learning-based mobility control in adaptive next-generation wireless networks.

[2] arXiv:2508.03095 [中文pdf, pdf, html, 其他]

标题： AI代理注册解决方案综述 显示英文标题

标题： A Survey of AI Agent Registry Solutions

Aditi Singh, Abul Ehtesham, Ramesh Raskar, Mahesh Lambe, Pradyumna Chari, Jared James Grogan, Abhishek Singh, Saket Kumar

主题： 网络与互联网架构 (cs.NI) ; 人工智能 (cs.AI) ; 多智能体系统 (cs.MA)

随着自主AI代理在云、企业及去中心化环境中扩展，建立标准化注册系统以支持发现、身份和能力共享的需求变得至关重要。 本文综述了三种突出的注册方法，每种方法由独特的元数据模型定义：MCP的mcp.json，A2A的Agent Card，以及NANDA的AgentFacts。 MCP使用带有GitHub认证发布的集中式元注册表，并为服务器发现提供结构化元数据。 A2A通过基于JSON的Agent Cards实现去中心化交互，可通过众所周知的URI、精选目录或直接配置进行发现。 NANDA Index引入了AgentFacts，这是一种密码学可验证且隐私保护的元数据模型，专为动态发现、凭据能力及跨域互操作性而设计。 这些方法在四个维度上进行了比较：安全性、可扩展性、认证和可维护性。 本文最后提出了建议和推荐，以指导未来针对AI代理互联网的注册系统的设计和采用。 显示英文摘要

As As autonomous AI agents scale across cloud, enterprise, and decentralized environments, the need for standardized registry systems to support discovery, identity, and capability sharing has become essential. This paper surveys three prominent registry approaches each defined by a unique metadata model: MCP's mcp.json, A2A's Agent Card, and NANDA's AgentFacts. MCP uses a centralized metaregistry with GitHub authenticated publishing and structured metadata for server discovery. A2A enables decentralized interaction via JSON-based Agent Cards, discoverable through well-known URIs, curated catalogs, or direct configuration. NANDA Index introduces AgentFacts, a cryptographically verifiable and privacy-preserving metadata model designed for dynamic discovery, credentialed capabilities, and cross-domain interoperability. These approaches are compared across four dimensions: security, scalability, authentication, and maintainability. The paper concludes with suggestions and recommendations to guide future design and adoption of registry systems for the Internet of AI Agents.

[3] arXiv:2508.03101 [中文pdf, pdf, html, 其他]

标题： 在实践中使用NANDA索引架构：企业视角 显示英文标题

标题： Using the NANDA Index Architecture in Practice: An Enterprise Perspective

Sichao Wang, Ramesh Raskar, Mahesh Lambe, Pradyumna Chari, Rekha Singhal, Shailja Gupta, Rajesh Ranjan, Ken Huang

主题： 网络与互联网架构 (cs.NI) ; 人工智能 (cs.AI) ; 多智能体系统 (cs.MA)

自主AI代理的普及代表了从传统网络架构向需要复杂发现、认证、能力验证和跨异构协议环境安全协作机制的协作智能系统范式的转变。 本文提出一个全面的框架，解决安全、可信和互操作的AI代理生态系统的基本基础设施需求。 我们引入了NANDA（去中心化架构中的联网AI代理）框架，提供全局代理发现、通过AgentFacts进行密码学验证的能力证明，以及在Anthropic的Modal Context Protocol (MCP)、Google的Agent-to-Agent (A2A)、Microsoft的NLWeb和标准HTTPS通信之间的跨协议互操作性。 NANDA实现了零信任代理访问（ZTAA）原则，将传统的零信任网络访问（ZTNA）扩展到解决自主代理安全挑战，包括能力欺骗、身份伪装攻击和敏感数据泄露。 该框架定义了代理可见性和控制（AVC）机制，使企业治理成为可能，同时保持操作自主性和监管合规性。 我们的方法将孤立的AI代理转变为可验证、可信的智能服务互联生态系统，为大规模自主代理在企业及消费者环境中的部署建立基础基础设施。 这项工作解决了当前AI代理能力与安全、可扩展的多代理协作基础设施需求之间的关键差距，为下一代自主智能系统奠定了基础。 显示英文摘要

The proliferation of autonomous AI agents represents a paradigmatic shift from traditional web architectures toward collaborative intelligent systems requiring sophisticated mechanisms for discovery, authentication, capability verification, and secure collaboration across heterogeneous protocol environments. This paper presents a comprehensive framework addressing the fundamental infrastructure requirements for secure, trustworthy, and interoperable AI agent ecosystems. We introduce the NANDA (Networked AI Agents in a Decentralized Architecture) framework, providing global agent discovery, cryptographically verifiable capability attestation through AgentFacts, and cross-protocol interoperability across Anthropic's Modal Context Protocol (MCP), Google's Agent-to-Agent (A2A), Microsoft's NLWeb, and standard HTTPS communications. NANDA implements Zero Trust Agentic Access (ZTAA) principles, extending traditional Zero Trust Network Access (ZTNA) to address autonomous agent security challenges including capability spoofing, impersonation attacks, and sensitive data leakage. The framework defines Agent Visibility and Control (AVC) mechanisms enabling enterprise governance while maintaining operational autonomy and regulatory compliance. Our approach transforms isolated AI agents into an interconnected ecosystem of verifiable, trustworthy intelligent services, establishing foundational infrastructure for large-scale autonomous agent deployment across enterprise and consumer environments. This work addresses the critical gap between current AI agent capabilities and infrastructure requirements for secure, scalable, multi-agent collaboration, positioning the foundation for next-generation autonomous intelligent systems.

[4] arXiv:2508.03113 [中文pdf, pdf, 其他]

标题： NANDA自适应解析器：AI代理名称动态解析架构 显示英文标题

标题： NANDA Adaptive Resolver: Architecture for Dynamic Resolution of AI Agent Names

John Zinky, Hema Seshadri, Mahesh Lambe, Pradyumna Chari, Ramesh Raskar

主题： 网络与互联网架构 (cs.NI) ; 人工智能 (cs.AI) ; 多智能体系统 (cs.MA)

自适应解析器是一种动态微服务架构，旨在解决在分布式、异构环境中人工智能代理通信的静态端点解析的局限性。 与传统的DNS或静态URL不同， 自适应解析器可以根据地理位置、系统负载、代理能力以及安全威胁等因素，实现上下文感知的实时通信端点选择。 代理通过代理事实卡在代理注册表/索引中宣传其代理名称和上下文需求。 请求代理使用注册表来发现目标代理。 请求代理随后可以将目标代理名称解析为根据代理之间的实际环境上下文定制的通信通道。 该架构支持信任、服务质量和服务资源约束的协商，促进超越传统客户端-服务器模型的灵活、安全和可扩展的代理间交互。 自适应解析器为稳健、未来可靠的代理通信提供了基础，能够随着生态系统复杂性的增加而不断发展。 显示英文摘要

AdaptiveResolver is a dynamic microservice architecture designed to address the limitations of static endpoint resolution for AI agent communication in distributed, heterogeneous environments. Unlike traditional DNS or static URLs, AdaptiveResolver enables context-aware, real-time selection of communication endpoints based on factors such as geographic location, system load, agent capabilities, and security threats. Agents advertise their Agent Name and context requirements through Agent Fact cards in an Agent Registry/Index. A requesting Agent discovers a Target Agent using the registry. The Requester Agent can then resolve the Target Agent Name to obtain a tailored communication channel to the agent based on actual environmental context between the agents. The architecture supports negotiation of trust, quality of service, and resource constraints, facilitating flexible, secure, and scalable agent-to-agent interactions that go beyond the classic client-server model. AdaptiveResolver provides a foundation for robust, future-proof agent communication that can evolve with increasing ecosystem complexity.

[5] arXiv:2508.03146 [中文pdf, pdf, html, 其他]

标题： IEEE 802.11ah 物联网部署的可扩展性与性能评估：测试平台方法 显示英文标题

标题： Scalability and Performance Evaluation of IEEE 802.11ah IoT Deployments: A Testbed Approach

Kostas Chounos, Katerina Kyriakou, Thanasis Korakis

主题： 网络与互联网架构 (cs.NI)

这项工作专注于现代无线物联网（IoT）架构的开发和评估，与新兴的5G及未来应用相关。为了分析数据需求的增长及其影响，我们构建了一个IEEE 802.11ah（WiFi Halow）办公室测试平台，用于实际实验。这种部署使我们能够揭示在各种具有挑战性的场景下，此类网络的实际性能和可扩展性限制。据我们所知，这是首次研究复杂的现实世界IEEE 802.11ah实现，特别旨在揭示意外的性能行为，例如在紧密部署的无线链路中出现的显著吞吐量下降。我们的研究结果表明，激烈的网络竞争和邻道干扰（ACI）极大地影响了涉及的无线链路的性能。除了评估网络性能外，我们的实验分析还考虑了被测设备的能量消耗，为IEEE 802.11ah在现实世界部署中的可行性提供了更全面的视角。对这些意外现象的有效披露，可以在物联网到云的连续体中促成良好的决策和能量消耗优化。 显示英文摘要

This work focuses on the development and assessment of modern wireless Internet of Things (IoT) architectures, with relevance to emerging 5G and beyond applications. To analyze the growing demands for data, and their impact, we built an IEEE 802.11ah (WiFi Halow) office testbed for real-world experimentation. This deployment allows us to uncover the practical performance and scalability limitations of such networks under various challenging scenarios. To the best of our knowledge, this is the first study to consider complex real-world IEEE 802.11ah implementations, aiming specifically to reveal unexpected performance behaviors, such as significant throughput degradation arising in closely deployed wireless links. Our findings show that intense network contention and Adjacent Channel Interference (ACI), drastically impact the performance of the wireless links involved. Beyond evaluating network performance, our experimental analysis also considers the energy consumption of the devices under test, offering a more holistic perspective on the feasibility of IEEE 802.11ah in real-world deployments. The effective disclosure of such unexpected phenomena, can lead to well planned decisions and energy consumption optimization across the IoT to Cloud continuum.

[6] arXiv:2508.03171 [中文pdf, pdf, html, 其他]

标题： 用于无人机通信的节能联邦学习 显示英文标题

标题： Energy-efficient Federated Learning for UAV Communications

Chien-Wei Fu, Meng-Lin Ku

主题： 网络与互联网架构 (cs.NI) ; 信息论 (cs.IT)

本文中，我们提出了一种无人机（UAV）辅助的联邦学习（FL）框架，该框架联合优化无人机轨迹、用户参与、功率分配和数据量控制，以最小化整体系统能耗。 我们首先推导了在多个本地更新下的FL模型的收敛精度，从而实现了对用户参与和数据量如何影响FL学习性能的理论理解。 得到的联合优化问题是非凸的；为了解决这个问题，我们采用交替优化（AO）和逐次凸逼近（SCA）技术来凸化非凸约束，从而设计了一个迭代能耗优化（ECO）算法。 仿真结果证实，ECO始终优于现有的基线方案。 显示英文摘要

In this paper, we propose an unmanned aerial vehicle (UAV)-assisted federated learning (FL) framework that jointly optimizes UAV trajectory, user participation, power allocation, and data volume control to minimize overall system energy consumption. We begin by deriving the convergence accuracy of the FL model under multiple local updates, enabling a theoretical understanding of how user participation and data volume affect FL learning performance. The resulting joint optimization problem is non-convex; to address this, we employ alternating optimization (AO) and successive convex approximation (SCA) techniques to convexify the non-convex constraints, leading to the design of an iterative energy consumption optimization (ECO) algorithm. Simulation results confirm that ECO consistently outperform existing baseline schemes.

[7] arXiv:2508.03287 [中文pdf, pdf, html, 其他]

标题： 基于性能特征分析的5G网络中函数卸载的指令 显示英文标题

标题： Directives for Function Offloading in 5G Networks Based on a Performance Characteristics Analysis

Falk Dettinger, Matthias Weiß, Daniel Baumann, Martin Sommer, Michael Weyrich

评论： 7页，4图

主题： 网络与互联网架构 (cs.NI) ; 分布式、并行与集群计算 (cs.DC)

基于云的卸载有助于解决执行资源密集型车辆算法时的能耗和性能挑战。 利用5G，其低延迟和高带宽，可以实现车辆与云的无缝集成。 目前，只有非独立5G是公开可用的，与理论研究相比，实际应用仍处于探索阶段。 本文评估了5G非独立网络在车辆功能云执行中的应用，重点研究了延迟、往返时间以及数据包交付。 测试使用了两种基于人工智能的算法——情绪识别和物体识别——在德国巴登-符腾堡州8.8公里的路线上进行，涵盖了城市、乡村和森林区域。 分析了两个平台：法兰克福的云边缘节点和曼海姆的云，采用了各种部署策略，如传统应用程序和容器化及容器编排设置。 关键发现表明，平均信号质量为84%，尽管在建筑区有轻微下降，但没有出现连接中断。 数据包分析显示，两种算法的数据包错误率均低于0.1%。 传输时间因地理位置和后端服务器的网络连接而显著不同，而处理时间主要受所用计算硬件的影响。 此外，云卸载似乎只有在往返时间超过150毫秒的情况下才是可行的选择。 显示英文摘要

Cloud-based offloading helps address energy consumption and performance challenges in executing resource-intensive vehicle algorithms. Utilizing 5G, with its low latency and high bandwidth, enables seamless vehicle-to-cloud integration. Currently, only non-standalone 5G is publicly available, and real-world applications remain underexplored compared to theoretical studies. This paper evaluates 5G non-standalone networks for cloud execution of vehicle functions, focusing on latency, Round Trip Time, and packet delivery. Tests used two AI-based algorithms -- emotion recognition and object recognition -- along an 8.8 km route in Baden-W\"urttemberg, Germany, encompassing urban, rural, and forested areas. Two platforms were analyzed: a cloudlet in Frankfurt and a cloud in Mannheim, employing various deployment strategies like conventional applications and containerized and container-orchestrated setups. Key findings highlight an average signal quality of 84 %, with no connectivity interruptions despite minor drops in built-up areas. Packet analysis revealed a Packet Error Rate below 0.1 % for both algorithms. Transfer times varied significantly depending on the geographical location and the backend servers' network connections, while processing times were mainly influenced by the computation hardware in use. Additionally, cloud offloading seems only be a suitable option, when a round trip time of more than 150 ms is possible.

[8] arXiv:2508.03321 [中文pdf, pdf, html, 其他]

标题： 双向TLS握手缓存用于受限工业物联网场景 显示英文标题

标题： Bidirectional TLS Handshake Caching for Constrained Industrial IoT Scenarios

Jörn Bodenhausen, Simon Mangel, Thomas Vogt, Martin Henze

评论： 已接受发表于2025年IEEE第50届局域计算机网络会议（LCN）论文集

主题： 网络与互联网架构 (cs.NI) ; 密码学与安全 (cs.CR)

虽然TLS已经成为端到端安全的事实标准，但在不断发展的工业物联网场景中，由于设备和网络的普遍资源限制，其用于保护关键通信的能力受到严重限制。 最明显的是，建立安全连接的TLS握手会带来显著的带宽和处理开销，这在资源受限的环境中通常无法处理。 为了缓解这种情况，我们提出了BiTHaC，它通过利用重复TLS握手的大部分内容，尤其是证书，是静态的，从而实现了双向TLS握手缓存。 因此，不需要传输冗余信息，也不需要执行相应的计算，从而节省宝贵的带宽和处理资源。 通过为wolfSSL实现BiTHaC，我们证明可以将TLS握手的带宽消耗减少多达61.1%，计算开销减少多达8.5%，同时仅产生可管理的内存开销，并保持TLS的严格安全保证。 显示英文摘要

While TLS has become the de-facto standard for end-to-end security, its use to secure critical communication in evolving industrial IoT scenarios is severely limited by prevalent resource constraints of devices and networks. Most notably, the TLS handshake to establish secure connections incurs significant bandwidth and processing overhead that often cannot be handled in constrained environments. To alleviate this situation, we present BiTHaC which realizes bidirectional TLS handshake caching by exploiting that significant parts of repeated TLS handshakes, especially certificates, are static. Thus, redundant information neither needs to be transmitted nor corresponding computations performed, saving valuable bandwidth and processing resources. By implementing BiTHaC for wolfSSL, we show that we can reduce the bandwidth consumption of TLS handshakes by up to 61.1% and the computational overhead by up to 8.5%, while incurring only well-manageable memory overhead and preserving the strict security guarantees of TLS.

[9] arXiv:2508.03674 [中文pdf, pdf, html, 其他]

标题： Morphlux：用于机器学习的多加速器服务器中可编程的芯片间光子织物 显示英文标题

标题： Morphlux: Programmable chip-to-chip photonic fabrics in multi-accelerator servers for ML

Abhishek Vijaya Kumar, Eric Ding, Arjun Devraj, Rachee Singh

主题： 网络与互联网架构 (cs.NI) ; 硬件架构 (cs.AR) ; 机器学习 (cs.LG)

我们使用新出现的可编程芯片间光子织物，在计算服务器内对加速器芯片（例如，GPU、TPU）进行光学互连。 相反，目前，作为机器学习工作主力的商用多加速器计算服务器，使用电气互连来在网络中连接服务器内的加速器芯片。 然而，最近的趋势表明，由于加速器FLOPS的扩展速度比同一服务器内加速器之间的互连带宽更快，导致了互连带宽墙。 这导致了云数据中心中GPU资源的利用率低下和空闲。 我们开发了Morphlux，一种服务器规模的可编程光子织物，用于在服务器内互连加速器。 我们证明，将Morphlux添加到最先进的光子ML中心数据中心可以将租户计算分配的带宽提高多达66%，并将计算碎片减少多达70%。 我们开发了Morphlux的新型端到端硬件原型，以展示这些性能优势，这转化为ML模型训练吞吐量1.72倍的提升。 通过在我们的硬件测试平台中快速编程服务器规模的织物，Morphlux可以在1.2秒内逻辑上替换一个故障的加速器芯片。 显示英文摘要

We optically interconnect accelerator chips (e.g., GPUs, TPUs) within compute servers using newly viable programmable chip-to-chip photonic fabrics. In contrast, today, commercial multi-accelerator compute servers that are workhorses of ML, use electrical interconnects to network accelerator chips in the server. However, recent trends have shown an interconnect bandwidth wall caused by accelerator FLOPS scaling at a faster rate than the bandwidth of the interconnect between accelerators in the same server. This has led to under-utilization and idling of GPU resources in cloud datacenters. We develop Morphlux, a server-scale programmable photonic fabric, to interconnect accelerators within servers. We show that augmenting state-of-the-art photonic ML-centric datacenters with Morphlux can improve the bandwidth of tenant compute allocations by up to 66% and reduce compute fragmentation by up to 70%. We develop a novel end-to-end hardware prototype of Morphlux to demonstrate these performance benefits, which translate to 1.72x improvement in training throughput of ML models. By rapidly programming the server-scale fabric in our hardware testbed, Morphlux can logically replace a failed accelerator chip in 1.2 seconds.

交叉提交 (展示 4 之 4 条目 )

[10] arXiv:2508.02856 (交叉列表自 eess.SP) [中文pdf, pdf, html, 其他]

标题： 带有主动-ISAC防御的毫米波安全波束赋形以对抗波束窃取攻击 显示英文标题

标题： Secure mmWave Beamforming with Proactive-ISAC Defense Against Beam-Stealing Attacks

Seyed Bagher Hashemi Natanzi, Hossein Mohammadi, Bo Tang, Vuk Marojevic

主题： 信号处理 (eess.SP) ; 人工智能 (cs.AI) ; 网络与互联网架构 (cs.NI)

毫米波（mmWave）通信系统面临越来越容易受到先进波束窃取攻击的威胁，这对物理层安全构成了重大威胁。 本文介绍了一个新颖的框架，采用先进的深度强化学习（DRL）代理，以主动和自适应的方式防御这些复杂的攻击。 一个关键创新是利用集成感知与通信（ISAC）能力进行主动、智能的威胁评估。 基于近端策略优化（PPO）算法构建的DRL代理，动态控制ISAC探测动作以调查可疑活动。 我们引入了一种密集的课程学习策略，确保代理在训练过程中经历成功的检测，以克服此类安全关键任务固有的复杂探索挑战。 因此，代理学习到一种稳健且自适应的策略，能够智能地平衡安全性和通信性能。 数值结果表明，我们的框架在保持平均用户SINR超过13 dB的同时，实现了92.8%的平均攻击者检测率。 显示英文摘要

Millimeter-wave (mmWave) communication systems face increasing susceptibility to advanced beam-stealing attacks, posing a significant physical layer security threat. This paper introduces a novel framework employing an advanced Deep Reinforcement Learning (DRL) agent for proactive and adaptive defense against these sophisticated attacks. A key innovation is leveraging Integrated Sensing and Communications (ISAC) capabilities for active, intelligent threat assessment. The DRL agent, built on a Proximal Policy Optimization (PPO) algorithm, dynamically controls ISAC probing actions to investigate suspicious activities. We introduce an intensive curriculum learning strategy that guarantees the agent experiences successful detection during training to overcome the complex exploration challenges inherent to such a security-critical task. Consequently, the agent learns a robust and adaptive policy that intelligently balances security and communication performance. Numerical results demonstrate that our framework achieves a mean attacker detection rate of 92.8% while maintaining an average user SINR of over 13 dB.

[11] arXiv:2508.03579 (交叉列表自 cs.LG) [中文pdf, pdf, html, 其他]

标题： 无感知异构的鲁棒联邦学习 显示英文标题

标题： Heterogeneity-Oblivious Robust Federated Learning

Weiyao Zhang, Jinyang Li, Qi Song, Miao Wang, Chungang Lin, Haitong Luo, Xuying Meng, Yujun Zhang

评论： 待审核

主题： 机器学习 (cs.LG) ; 网络与互联网架构 (cs.NI)

联邦学习（FL）仍然极易受到中毒攻击，尤其是在现实世界的超异构环境下，客户端在数据分布、通信能力和模型架构方面存在显著差异。 这种异构性不仅削弱了聚合策略的有效性，也使攻击更难以检测。 此外，高维模型扩大了攻击面。 为应对这些挑战，我们提出了Horus，这是一个以低秩适应（LoRAs）为中心的无视异构性的鲁棒联邦学习框架。 Horus不是聚合完整的模型参数，而是将LoRAs插入经验上稳定的层，并仅聚合LoRAs以减少攻击面。我们发现了一个关键的实证观察结果，即在异构性和中毒情况下，输入投影（LoRA-A）比输出投影（LoRA-B）更加稳定。 利用这一点，我们设计了一个无视异构性的中毒评分，使用来自LoRA-A的特征来过滤中毒客户端。 对于剩余的良性客户端，我们提出了一种投影感知的聚合机制，在保留协作信号的同时抑制漂移，通过与全局方向的一致性对客户端更新进行重新加权。 在多种数据集、模型架构和攻击下的广泛实验表明，Horus在鲁棒性和准确性方面始终优于最先进的基线方法。 显示英文摘要

Federated Learning (FL) remains highly vulnerable to poisoning attacks, especially under real-world hyper-heterogeneity, where clients differ significantly in data distributions, communication capabilities, and model architectures. Such heterogeneity not only undermines the effectiveness of aggregation strategies but also makes attacks more difficult to detect. Furthermore, high-dimensional models expand the attack surface. To address these challenges, we propose Horus, a heterogeneity-oblivious robust FL framework centered on low-rank adaptations (LoRAs). Rather than aggregating full model parameters, Horus inserts LoRAs into empirically stable layers and aggregates only LoRAs to reduce the attack surface.We uncover a key empirical observation that the input projection (LoRA-A) is markedly more stable than the output projection (LoRA-B) under heterogeneity and poisoning. Leveraging this, we design a Heterogeneity-Oblivious Poisoning Score using the features from LoRA-A to filter poisoned clients. For the remaining benign clients, we propose projection-aware aggregation mechanism to preserve collaborative signals while suppressing drifts, which reweights client updates by consistency with the global directions. Extensive experiments across diverse datasets, model architectures, and attacks demonstrate that Horus consistently outperforms state-of-the-art baselines in both robustness and accuracy.

[12] arXiv:2508.03584 (交叉列表自 eess.SP) [中文pdf, pdf, html, 其他]

标题： 解码和工程化植物生物群通信以实现智能农业 显示英文标题

标题： Decoding and Engineering the Phytobiome Communication for Smart Agriculture

Fatih Gulec, Hamdan Awan, Nigel Wallbridge, Andrew W. Eckford

评论： 正在修订中，供IEEE通信杂志使用

主题： 信号处理 (eess.SP) ; 人工智能 (cs.AI) ; 新兴技术 (cs.ET) ; 网络与互联网架构 (cs.NI) ; 分子网络 (q-bio.MN)

智能农业应用将物联网和机器学习/人工智能（ML/AI）等技术整合到农业中，有望解决日益增长的粮食需求、环境污染和水资源短缺等现代挑战。 随着植物生物组（phytobiome）概念的提出，该概念定义了包括植物、其环境和相关生物在内的区域，以及分子通信（MC）的最新出现，利用通信理论来推进农业科学和实践存在重要机遇。 在本文中，我们旨在使用通信工程的视角，以全面理解植物生物组通信，并弥合植物生物组通信与智能农业之间的差距。 首先，介绍了通过分子和电生理信号进行植物生物组通信的概述，并提出了一个将植物生物组建模为通信网络的多尺度框架。 然后，通过植物实验展示了如何利用该框架对电生理信号进行建模。 此外，还提出了通过工程化植物生物组通信实现的智能农业应用，例如智能灌溉和农药的定向输送。 这些应用将ML/AI方法与由MC支持的生物纳米事物互联网相结合，为更高效、可持续和环保的农业生产铺平道路。 最后，讨论了这些应用的实施挑战、开放的研究问题和工业前景。 显示英文摘要

Smart agriculture applications, integrating technologies like the Internet of Things and machine learning/artificial intelligence (ML/AI) into agriculture, hold promise to address modern challenges of rising food demand, environmental pollution, and water scarcity. Alongside the concept of the phytobiome, which defines the area including the plant, its environment, and associated organisms, and the recent emergence of molecular communication (MC), there exists an important opportunity to advance agricultural science and practice using communication theory. In this article, we motivate to use the communication engineering perspective for developing a holistic understanding of the phytobiome communication and bridge the gap between the phytobiome communication and smart agriculture. Firstly, an overview of phytobiome communication via molecular and electrophysiological signals is presented and a multi-scale framework modeling the phytobiome as a communication network is conceptualized. Then, how this framework is used to model electrophysiological signals is demonstrated with plant experiments. Furthermore, possible smart agriculture applications, such as smart irrigation and targeted delivery of agrochemicals, through engineering the phytobiome communication are proposed. These applications merge ML/AI methods with the Internet of Bio-Nano-Things enabled by MC and pave the way towards more efficient, sustainable, and eco-friendly agricultural production. Finally, the implementation challenges, open research issues, and industrial outlook for these applications are discussed.

[13] arXiv:2508.03681 (交叉列表自 cs.IT) [中文pdf, pdf, html, 其他]

标题： 如果，但私密地：私密反事实检索 显示英文标题

标题： What If, But Privately: Private Counterfactual Retrieval

Shreya Meel, Mohamed Nomeir, Pasan Dissanayake, Sanghamitra Dutta, Sennur Ulukus

评论： arXiv管理员注释：与arXiv:2410.13812、arXiv:2411.10429文本重叠

主题： 信息论 (cs.IT) ; 密码学与安全 (cs.CR) ; 机器学习 (cs.LG) ; 网络与互联网架构 (cs.NI) ; 信号处理 (eess.SP)

透明性和可解释性是在高风险应用中使用黑盒机器学习模型时需要考虑的两个重要方面。 提供反事实解释是满足这一需求的一种方式。 然而，这也对提供解释的机构以及请求解释的用户的隐私构成威胁。 在本工作中，我们主要关注用户隐私，用户希望检索一个反事实实例，而无需向机构透露其特征向量。 我们的框架从接受点的数据库中检索精确的最近邻反事实解释，同时实现用户的信息理论隐私。 首先，我们引入了私有反事实检索（PCR）问题，并提出了一种基线PCR方案，该方案从机构的角度保持用户特征向量的信息理论隐私。 在此基础上，我们提出了另外两种方案，与基线方案相比，这些方案减少了泄露给用户的机构数据库信息量。 其次，我们放松了所有特征可变的假设，考虑了不可变PCR（I-PCR）的设置。 在此设置中，用户检索最近的反事实，而不改变其特征的一个私有子集，该子集构成不可变集，同时保持其特征向量和不可变集的隐私。 为此，我们提出了两种方案，这些方案在信息理论层面保护用户的隐私，但确保不同程度的数据库隐私。 第三，我们将我们的PCR和I-PCR方案扩展以包含用户对其属性转换的偏好，以便获得更具行动性的解释。 最后，我们提供了数值结果来支持我们的理论发现，并比较了所提方案的数据库泄露情况。 显示英文摘要

Transparency and explainability are two important aspects to be considered when employing black-box machine learning models in high-stake applications. Providing counterfactual explanations is one way of catering this requirement. However, this also poses a threat to the privacy of the institution that is providing the explanation, as well as the user who is requesting it. In this work, we are primarily concerned with the user's privacy who wants to retrieve a counterfactual instance, without revealing their feature vector to the institution. Our framework retrieves the exact nearest neighbor counterfactual explanation from a database of accepted points while achieving perfect, information-theoretic, privacy for the user. First, we introduce the problem of private counterfactual retrieval (PCR) and propose a baseline PCR scheme that keeps the user's feature vector information-theoretically private from the institution. Building on this, we propose two other schemes that reduce the amount of information leaked about the institution database to the user, compared to the baseline scheme. Second, we relax the assumption of mutability of all features, and consider the setting of immutable PCR (I-PCR). Here, the user retrieves the nearest counterfactual without altering a private subset of their features, which constitutes the immutable set, while keeping their feature vector and immutable set private from the institution. For this, we propose two schemes that preserve the user's privacy information-theoretically, but ensure varying degrees of database privacy. Third, we extend our PCR and I-PCR schemes to incorporate user's preference on transforming their attributes, so that a more actionable explanation can be received. Finally, we present numerical results to support our theoretical findings, and compare the database leakage of the proposed schemes.

替换提交 (展示 6 之 6 条目 )

[14] arXiv:2408.15609 (替换) [中文pdf, pdf, html, 其他]

标题： 业务导向网络中的统计服务质量提供 显示英文标题

标题： Statistical QoS Provision in Business-Centric Networks

Chang Wu, Yuang Chen, Hancheng Lu

评论： 19个图形

主题： 网络与互联网架构 (cs.NI) ; 机器学习 (cs.LG)

更精细的资源管理和服务质量（QoS）提供是无线通信技术的关键目标。 在本文中，我们提出了一种新颖的以业务为中心的网络（BCN），旨在基于一种跨层框架实现可扩展的QoS提供，该框架捕捉应用、传输参数和信道之间的关系。 我们研究了连续流和事件驱动流模型，并提出了吞吐量、延迟和可靠性的关键QoS指标。 通过联合考虑功率和带宽分配、传输参数以及跨层的接入点网络拓扑，我们优化了加权资源效率并实现了统计QoS提供。 为了解决参数之间的耦合问题，我们提出了一种新的深度强化学习（DRL）框架，即具有经验共享的异构参与者协作优化（COHA-ES）。 代表多个AP的功率和子信道（SC）参与者在统一批评者的指导下进行联合优化。 此外，我们引入了一种新的多线程经验共享机制，以加速训练并提高奖励。 大量的对比实验验证了我们的DRL框架在收敛性和效率方面的有效性。 此外，对比分析展示了BCN结构在提升频谱和能量效率方面的全面优势。 显示英文摘要

More refined resource management and Quality of Service (QoS) provisioning is a critical goal of wireless communication technologies. In this paper, we propose a novel Business-Centric Network (BCN) aimed at enabling scalable QoS provisioning, based on a cross-layer framework that captures the relationship between application, transport parameters, and channels. We investigate both continuous flow and event-driven flow models, presenting key QoS metrics such as throughput, delay, and reliability. By jointly considering power and bandwidth allocation, transmission parameters, and AP network topology across layers, we optimize weighted resource efficiency with statistical QoS provisioning. To address the coupling among parameters, we propose a novel deep reinforcement learning (DRL) framework, which is Collaborative Optimization among Heterogeneous Actors with Experience Sharing (COHA-ES). Power and sub-channel (SC) Actors representing multiple APs are jointly optimized under the unified guidance of a common critic. Additionally, we introduce a novel multithreaded experience-sharing mechanism to accelerate training and enhance rewards. Extensive comparative experiments validate the effectiveness of our DRL framework in terms of convergence and efficiency. Moreover, comparative analyses demonstrate the comprehensive advantages of the BCN structure in enhancing both spectral and energy efficiency.

[15] arXiv:2411.08767 (替换) [中文pdf, pdf, html, 其他]

标题： SANDWICH：面向离线、可微分、完全可训练的无线神经光线追踪代理 显示英文标题

标题： SANDWICH: Towards an Offline, Differentiable, Fully-Trainable Wireless Neural Ray-Tracing Surrogate

Yifei Jin, Ali Maatouk, Sarunas Girdzijauskas, Shugong Xu, Leandros Tassiulas, Rex Ying

评论： 被ICMLCN 2025接受

主题： 网络与互联网架构 (cs.NI) ; 人工智能 (cs.AI)

无线射线追踪（RT）正成为三维（3D）无线信道建模的关键工具，这得益于图形渲染技术的进步。当前的方法难以准确模拟高于5G（B5G）网络的信号，这些信号通常在更高频率下运行，并且更容易受到环境条件和变化的影响。现有的在线学习解决方案在训练期间需要实时的环境监督，这既昂贵又与基于GPU的处理不兼容。作为回应，我们提出了一种新方法，将射线轨迹生成重新定义为一个序列决策问题，利用生成模型联合学习每个指定环境中的光学、物理和信号特性。我们的工作引入了场景感知神经决策无线信道射线追踪层次结构（SANDWICH），这是一种创新的离线、完全可微的方法，可以在GPU上完全训练。与现有的在线学习方法相比，SANDWICH表现出更优越的性能，在RT精度上比基线高出4e^-2弧度，并且仅比顶级信道增益估计低0.5 dB。 显示英文摘要

Wireless ray-tracing (RT) is emerging as a key tool for three-dimensional (3D) wireless channel modeling, driven by advances in graphical rendering. Current approaches struggle to accurately model beyond 5G (B5G) network signaling, which often operates at higher frequencies and is more susceptible to environmental conditions and changes. Existing online learning solutions require real-time environmental supervision during training, which is both costly and incompatible with GPU-based processing. In response, we propose a novel approach that redefines ray trajectory generation as a sequential decision-making problem, leveraging generative models to jointly learn the optical, physical, and signal properties within each designated environment. Our work introduces the Scene-Aware Neural Decision Wireless Channel Raytracing Hierarchy (SANDWICH), an innovative offline, fully differentiable approach that can be trained entirely on GPUs. SANDWICH offers superior performance compared to existing online learning methods, outperforms the baseline by 4e^-2 radian in RT accuracy, and only fades 0.5 dB away from toplined channel gain estimation.

[16] arXiv:2504.17307 (替换) [中文pdf, pdf, html, 其他]

标题： 一种可扩展的GPU网络软件传输层 显示英文标题

标题： An Extensible Software Transport Layer for GPU Networking

Yang Zhou, Zhongjie Chen, Ziming Mao, ChonLam Lao, Shuo Yang, Pravein Govindan Kannan, Jiaqi Gao, Yilong Zhao, Yongji Wu, Kaichao You, Fengyuan Ren, Zhiying Xu, Costin Raiciu, Ion Stoica

主题： 网络与互联网架构 (cs.NI)

快速发展的机器学习（ML）工作负载对网络的要求越来越高。 然而，RDMA网卡上的主机网络传输难以进化，导致ML工作负载出现问题。 例如，单路径RDMA流量容易发生流碰撞，严重降低集体通信性能。 我们提出了UCCL，一个可扩展的软件传输层，用于进化GPU网络。 UCCL将现有RDMA网卡的数据路径和控制路径解耦，并在主机CPU上高效运行控制路径传输。 这种软件可扩展性带来了硬件无法实现的传输创新，例如多路径传输以解决流碰撞问题。 基于UCCL的ML集体操作相比现有的RDMA网卡性能最高提升4.5倍。 显示英文摘要

Fast-evolving machine learning (ML) workloads have increasing requirements for networking. However, host network transport on RDMA NICs is hard to evolve, causing problems for ML workloads. For example, single-path RDMA traffic is prone to flow collisions that severely degrade collective communication performance. We present UCCL, an extensible software transport layer to evolve GPU networking. UCCL decouples the data path and control path of existing RDMA NICs and efficiently runs the control-path transport on host CPUs. This software extensibility brings in transport innovations that cannot be achieved in hardware for ML workloads, e.g., a multipath transport to resolve flow collisions. ML collectives atop UCCL achieve up to 4.5x higher performance compared to existing RDMA NICs.

[17] arXiv:2507.13717 (替换) [中文pdf, pdf, html, 其他]

标题： ATRO：一种用于可重构数据中心网络拓扑工程的快速算法 显示英文标题

标题： ATRO: A Fast Algorithm for Topology Engineering of Reconfigurable Datacenter Networks

Yingming Mao, Qiaozhu Zhai, Ximeng Liu, Xinchi Han, Fafan li, Shizhen Zhao, Yuzhou Zhou, Zhen Yao, Xia Zhu

主题： 网络与互联网架构 (cs.NI)

可重构数据中心网络（DCN）通过光路交换机（OCS）增强了传统架构，使得跨机架链接的逻辑拓扑能够动态重新配置。 优化这种拓扑对于适应流量动态变化至关重要，但由于其组合性质而具有挑战性。 当需求可以分布在多条路径上时，复杂度进一步增加，需要同时优化拓扑和路由。 我们提出了交替拓扑和路由优化（ATRO），这是一个统一的框架，支持单跳拓扑优化（流量通过直接路径路由）和多跳联合优化（路由也进行优化）。 尽管这些设置在约束上有所不同，但两者都是组合难题，对基于求解器的方法构成挑战。 ATRO高效地解决了这两种情况：在单跳情况下，它通过加速二分搜索保证全局最优；在多跳情况下，它在拓扑和路由更新之间交替进行，其中路由步骤可以使用现有的流量工程（TE）方法进行加速。 ATRO支持热启动，并在迭代过程中单调地提高解决方案质量。 即使与无求解器的TE方法结合，ATRO仍然具有竞争力，形成一个完全无求解器的优化流程，在各种工作负载下的运行时间和最大链路利用率方面仍优于之前的方法。 显示英文摘要

Reconfigurable data center networks (DCNs) enhance traditional architectures with optical circuit switches (OCSs), enabling dynamic reconfiguration of inter-pod links, i.e., the logical topology. Optimizing this topology is crucial for adapting to traffic dynamics but is challenging due to its combinatorial nature. The complexity increases further when demands can be distributed across multiple paths, requiring joint optimization of topology and routing. We propose Alternating Topology and Routing Optimization (ATRO), a unified framework that supports both one-hop topology optimization (where traffic is routed via direct paths) and multi-hop joint optimization (where routing is also optimized). Although these settings differ in constraints, both are combinatorially hard and challenge solver-based methods. ATRO addresses both cases efficiently: in the one-hop case, it guarantees the global optimum via an accelerated binary search; in the multi-hop case, it alternates between topology and routing updates, with routing steps optionally accelerated by existing traffic engineering (TE) methods. ATRO supports warm-starting and improves solution quality monotonically across iterations. ATRO remains competitive even when paired with solver-free TE methods, forming a fully solver-free optimization pipeline that still outperforms prior approaches in runtime and maximum link utilization across diverse workloads.

[18] arXiv:2504.19613 (替换) [中文pdf, pdf, html, 其他]

标题： 光量子网络的自动配置协议 显示英文标题

标题： Automatic Configuration Protocols for Optical Quantum Networks

Amin Taherkhani, Andrew Todd, Kentaro Teramoto, Rodney Van Meter, Shota Nagayama

评论： 11页，7图

主题： 量子物理 (quant-ph) ; 网络与互联网架构 (cs.NI)

在量子网络能够扩展到实际规模之前，有许多部署和配置任务必须实现自动化。 目前，量子网络测试平台主要通过手动配置：网络节点由自由空间和光纤的组合构建，然后连接到共享的单光子探测器、时间到数字转换器和光开关。 这些连接的信息必须手动跟踪；标签错误可能导致实验失败和漫长的调试过程。 在本文中，我们提出了协议和算法来自动化这两种手动流程。 首先，我们解决自动识别量子网络节点与时间到数字转换器之间连接的问题。 然后，我们转向更复杂的挑战，即识别连接到量子网络光开关的节点。 这些协议的实现将有助于推动量子网络所需其他协议的发展，例如网络拓扑发现、链路质量监控、资源命名和路由。 我们希望本文能作为近期实现的路线图。 显示英文摘要

Before quantum networks can scale up to practical sizes, there are many deployment and configuration tasks that must be automated. Currently, quantum networking testbeds are largely manually configured: network nodes are constructed out of a combination of free-space and fiber optics before being connected to shared single-photon detectors, time-to-digital converters, and optical switches. Information about these connections must be tracked manually; mislabeling may result in experimental failure and protracted debugging sessions. In this paper, we propose protocols and algorithms to automate two such manual processes. First, we address the problem of automatically identifying connections between quantum network nodes and time-to-digital converters. Then, we turn to the more complex challenge of identifying the nodes attached to a quantum network's optical switches. Implementation of these protocols will help enable the development of other protocols necessary for quantum networks, such as network topology discovery, link quality monitoring, resource naming, and routing. We intend for this paper to serve as a roadmap for near-term implementation.

[19] arXiv:2506.19781 (替换) [中文pdf, pdf, html, 其他]

标题： 星链机器人：移动卫星通信的平台和数据集 显示英文标题

标题： The Starlink Robot: A Platform and Dataset for Mobile Satellite Communication

Boyi Liu, Qianyi Zhang, Qiang Yang, Jianhao Jiao, Jagmohan Chauhan, Dimitrios Kanoulas

主题： 机器人技术 (cs.RO) ; 网络与互联网架构 (cs.NI)

卫星通信与移动设备的集成代表了连接方式的一次范式转变，然而在运动和环境遮挡条件下的性能特征仍了解不足。 我们提出了星链机器人，这是首个配备星链卫星互联网的移动机器人平台，配有包括向上摄像头、激光雷达和惯性测量单元在内的综合传感器套件，旨在系统研究运动中的卫星通信性能。 我们的多模态数据集捕捉了在不同场景下同步的通信指标、运动动力学、天空可见性和三维环境背景，包括稳定状态运动、可变速度和不同的遮挡条件。 该平台和数据集使研究人员能够开发具有运动感知的通信协议，预测连接中断，并优化卫星通信以适应从智能手机到自动驾驶汽车的新兴移动应用。 在本工作中，我们使用LEOViz进行实时卫星跟踪和数据收集。 星链机器人项目可在 https://github.com/StarlinkRobot 获取。 显示英文摘要

The integration of satellite communication into mobile devices represents a paradigm shift in connectivity, yet the performance characteristics under motion and environmental occlusion remain poorly understood. We present the Starlink Robot, the first mobile robotic platform equipped with Starlink satellite internet, comprehensive sensor suite including upward-facing camera, LiDAR, and IMU, designed to systematically study satellite communication performance during movement. Our multi-modal dataset captures synchronized communication metrics, motion dynamics, sky visibility, and 3D environmental context across diverse scenarios including steady-state motion, variable speeds, and different occlusion conditions. This platform and dataset enable researchers to develop motion-aware communication protocols, predict connectivity disruptions, and optimize satellite communication for emerging mobile applications from smartphones to autonomous vehicles. In this work, we use LEOViz for real-time satellite tracking and data collection. The starlink robot project is available at https://github.com/StarlinkRobot.