2023 IEEE 48th Conference on Local Computer Networks (LCN)最新文献_第3页

Cellular network offloading through Drone Cooperation 通过无人机合作卸载蜂窝网络

2023 IEEE 48th Conference on Local Computer Networks (LCN) Pub Date : 2023-10-02 DOI: 10.1109/lcn58197.2023.10223353

Gatien Roujanski, M. Marot, Hossam Afifi, Adel Mounir

引用次数: 0

Demo: Agent-Based Crowdsensing Simulation for Urban Meteorological Data Collection and Hybrid Aerial-Terrestrial Route Determination 演示:基于agent的城市气象数据采集和地空混合航路确定的众感仿真

2023 IEEE 48th Conference on Local Computer Networks (LCN) Pub Date : 2023-10-02 DOI: 10.1109/lcn58197.2023.10223330

Jose A. Gonzalez Nuñez, M. Akbaş

引用次数: 0

Leveraging Explainable AI Methods Towards Identifying Classification Issues on IDS Datasets 利用可解释的人工智能方法识别IDS数据集上的分类问题

2023 IEEE 48th Conference on Local Computer Networks (LCN) Pub Date : 2023-10-02 DOI: 10.1109/lcn58197.2023.10223401

Eric Lanfer, Sophia Sylvester, Nils Aschenbruck, Martin Atzmueller

引用次数: 1

XLab-UUV – A Virtual Testbed for Extra-Large Uncrewed Underwater Vehicles XLab-UUV -超大型无人潜航器虚拟测试平台

2023 IEEE 48th Conference on Local Computer Networks (LCN) Pub Date : 2023-10-02 DOI: 10.1109/lcn58197.2023.10223405

Konrad Wolsing, Antoine Saillard, Elmar Padilla, Jan Bauer

引用次数: 0

A Ship Honeynet to Gather Cyber Threat Intelligence for the Maritime Sector 船舶蜜网为海事部门收集网络威胁情报

2023 IEEE 48th Conference on Local Computer Networks (LCN) Pub Date : 2023-10-02 DOI: 10.1109/lcn58197.2023.10223347

Jeroen Pijpker, Stephen James McCombie

引用次数: 0

Effective Resource Allocation and Pricing Mechanism for MEC under Two-Price Equilibrium 两价均衡下MEC的有效资源配置与定价机制

2023 IEEE 48th Conference on Local Computer Networks (LCN) Pub Date : 2023-10-02 DOI: 10.1109/lcn58197.2023.10223350

Ying Li, Junwu Zhu, Xu Liu

引用次数: 0

Trusted Sharing of Data Under Cloud-Edge-End Collaboration and Its Formal Verification 云边缘协作下的可信数据共享及其形式化验证

2023 IEEE 48th Conference on Local Computer Networks (LCN) Pub Date : 2023-10-02 DOI: 10.1109/lcn58197.2023.10223319

Xuejian Li, Mingguang Wang

引用次数: 0

Trade-Off Between Compression and FEC in Image Transmission Over Wifibroadcast 无线广播图像传输中压缩与FEC的权衡

2023 IEEE 48th Conference on Local Computer Networks (LCN) Pub Date : 2023-10-02 DOI: 10.1109/lcn58197.2023.10223382

Nikolas Wintering, Jannis Mast, T. Hänel, Nils Aschenbruck

引用次数: 0

Design and Implementation of a Gateway Buoy for the Underwater-IoT 水下物联网网关浮标的设计与实现

2023 IEEE 48th Conference on Local Computer Networks (LCN) Pub Date : 2023-10-02 DOI: 10.1109/lcn58197.2023.10223369

Gunnar Schneider, Michael Goetz, I. Nissen

引用次数: 0

Meta-ATMoS+: A Meta-Reinforcement Learning Framework for Threat Mitigation in Software-Defined Networks Meta-ATMoS+:用于软件定义网络威胁缓解的元强化学习框架

2023 IEEE 48th Conference on Local Computer Networks (LCN) Pub Date : 2023-10-02 DOI: 10.1109/lcn58197.2023.10223403

Hauton Tsang, M. A. Salahuddin, Noura Limam, R. Boutaba

{"title":"Meta-ATMoS+: A Meta-Reinforcement Learning Framework for Threat Mitigation in Software-Defined Networks","authors":"Hauton Tsang, M. A. Salahuddin, Noura Limam, R. Boutaba","doi":"10.1109/lcn58197.2023.10223403","DOIUrl":"https://doi.org/10.1109/lcn58197.2023.10223403","url":null,"abstract":"—As cyber threats become increasingly common, automated threat mitigation solutions are more necessary than ever. Conventional threat mitigation frameworks are difﬁcult to tune for different network environments, but frameworks utilizing deep reinforcement learning (RL) have been proven to be an effective approach that can adapt to different networks automatically. Existing RL-based frameworks have shown to be generalizable to different network sizes and threats, and robust to false positives. However, training RL agents for these frameworks can be challenging in a production environment as the training process is time-consuming and disruptive to the production network. Hence, a staging environment is required to effectively train them. In this paper, we propose Meta-ATMoS+, a meta-RL framework for threat mitigation in software-deﬁned networks. We leverage Model-Agnostic Meta-Learning (MAML) to ﬁnd an initialization for the RL agent that generalizes to a variety of different network conﬁgurations. We show that the RL agent with MAML-learned initialization can accomplish few-shot learning on a target network with comparable performance to training on a staging environment. Few-shot learning not only allows the model to be trainable directly in the production environment but also enables human-in-the-loop RL for the mitigation of threats that do not have an easily-deﬁnable reward function.","PeriodicalId":178458,"journal":{"name":"2023 IEEE 48th Conference on Local Computer Networks (LCN)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124609935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0