Due to the complex nature of Advanced Persistent Threats (APTs) and their rapid evolvement, comprehensive datasets are needed to understand them. However, acquiring such datasets remains a challenge due to the lack of precise reports describing the attacks, realistic emulation, the extensive attack diversity, and concerns regarding data privacy. In this letter, we built a testbed for APTs and implemented 23 campaigns for 12 APTs using MITRE Caldera. For each campaign, we share the adversary profile, the abilities, the low-level telemetries, and the MITRE techniques. By making this comprehensive dataset openly accessible, our work supports academia and industry to strengthen cybersecurity research and develop robust defenses against the constantly evolving APTs.
{"title":"Comprehensive Advanced Persistent Threats Dataset","authors":"Abdussamad Syed;Boubakr Nour;Makan Pourzandi;Chadi Assi;Mourad Debbabi","doi":"10.1109/LNET.2025.3551989","DOIUrl":"https://doi.org/10.1109/LNET.2025.3551989","url":null,"abstract":"Due to the complex nature of Advanced Persistent Threats (APTs) and their rapid evolvement, comprehensive datasets are needed to understand them. However, acquiring such datasets remains a challenge due to the lack of precise reports describing the attacks, realistic emulation, the extensive attack diversity, and concerns regarding data privacy. In this letter, we built a testbed for APTs and implemented 23 campaigns for 12 APTs using MITRE Caldera. For each campaign, we share the adversary profile, the abilities, the low-level telemetries, and the MITRE techniques. By making this comprehensive dataset openly accessible, our work supports academia and industry to strengthen cybersecurity research and develop robust defenses against the constantly evolving APTs.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"7 2","pages":"150-154"},"PeriodicalIF":0.0,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308553","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}
Pub Date : 2025-03-13DOI: 10.1109/LNET.2025.3550931
Gaurav Kumar Pandey;Devendra Singh Gurjar;Suneel Yadav;Xingwang Li
This letter considers UAV-assisted data collection from energy-constrained Internet of Things (IoT) devices. Herein, a UAV utilizes radio frequency-based wireless power transfer technique to charge multiple IoT devices or schedules one IoT device to transmit its sensed data. Using the harvested energy, the IoT devices share the collected data with the UAV as per their schedule. For this setup, we aim to minimize IoT devices’ average Age of Information (AoI) by optimally controlling the UAV’s trajectory and scheduling of IoT devices while adhering to the energy consumption limitations of UAV and IoT devices. Considering the dynamic scenario for the considered network, the optimization problem is modeled as a Markov Decision Process and solved through dueling double deep Q-networks (D3QN) algorithm. The simulation results show that the proposed framework outperforms the baseline methods in reducing the average AoI of the IoT devices.
{"title":"Deep Reinforcement Learning for AoI-Aware UAV-Assisted Networks With RF Energy Harvesting","authors":"Gaurav Kumar Pandey;Devendra Singh Gurjar;Suneel Yadav;Xingwang Li","doi":"10.1109/LNET.2025.3550931","DOIUrl":"https://doi.org/10.1109/LNET.2025.3550931","url":null,"abstract":"This letter considers UAV-assisted data collection from energy-constrained Internet of Things (IoT) devices. Herein, a UAV utilizes radio frequency-based wireless power transfer technique to charge multiple IoT devices or schedules one IoT device to transmit its sensed data. Using the harvested energy, the IoT devices share the collected data with the UAV as per their schedule. For this setup, we aim to minimize IoT devices’ average Age of Information (AoI) by optimally controlling the UAV’s trajectory and scheduling of IoT devices while adhering to the energy consumption limitations of UAV and IoT devices. Considering the dynamic scenario for the considered network, the optimization problem is modeled as a Markov Decision Process and solved through dueling double deep Q-networks (D3QN) algorithm. The simulation results show that the proposed framework outperforms the baseline methods in reducing the average AoI of the IoT devices.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"7 2","pages":"88-92"},"PeriodicalIF":0.0,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308385","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}
This letter presents an adaptive trust architecture that enables secure, low-latency communication in 6G-enabled Internet of Things (IoT) networks, centering around a novel Adaptive Zero Trust Manager (AZTM) deployed at the network edge. Integrating zero trust principles with a lightweight, consensus-free blockchain, AZTM provides real-time authentication and behavior-based trust evaluation while maintaining energy efficiency. It supports secure device communication through dynamic key exchange, eliminating reliance on pre-shared secrets or centralized trust authorities. The system is validated through implementation on resource-constrained IoT devices, demonstrating low-latency performance, resilience to common attacks, and suitability for mission-critical 6G applications such as healthcare, industrial automation, and intelligent transport.
{"title":"Adaptive Trust Architecture for Secure IoT Communication in 6G","authors":"Ijaz Ahmad;Shakthi Gimhana;Ijaz Ahmad;Erkki Harjula","doi":"10.1109/LNET.2025.3566909","DOIUrl":"https://doi.org/10.1109/LNET.2025.3566909","url":null,"abstract":"This letter presents an adaptive trust architecture that enables secure, low-latency communication in 6G-enabled Internet of Things (IoT) networks, centering around a novel Adaptive Zero Trust Manager (AZTM) deployed at the network edge. Integrating zero trust principles with a lightweight, consensus-free blockchain, AZTM provides real-time authentication and behavior-based trust evaluation while maintaining energy efficiency. It supports secure device communication through dynamic key exchange, eliminating reliance on pre-shared secrets or centralized trust authorities. The system is validated through implementation on resource-constrained IoT devices, demonstrating low-latency performance, resilience to common attacks, and suitability for mission-critical 6G applications such as healthcare, industrial automation, and intelligent transport.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"7 2","pages":"113-116"},"PeriodicalIF":0.0,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10985891","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-01DOI: 10.1109/LNET.2025.3566243
Sankalp;Lata;Gaurang Sondur;Mahendra K. Shukla;Om Jee Pandey;Maxime Guillaud
The use of deep learning (DL) in communication systems shows great promise, particularly through DL-based physical-layer techniques with autoencoders (AEs) for end-to-end learning. This letter presents an AE-based DL framework to enhance physical-layer security in scenarios where multiple transmitters communicate with the receiver under eavesdropping threats, specifically within a Gaussian multiple-access wiretap channel. A key feature is a friendly jammer that emits a high-power Gaussian signal to disrupt eavesdroppers. The proposed framework is particularly relevant for security-critical applications such as wireless health monitoring systems, where safeguarding sensitive data is paramount. We assess secrecy performance by analyzing the symbol error rate among users in the presence of both an eavesdropper and a jammer. Simulation results show that our DL-based Gaussian jamming strategy significantly improves secrecy performance, effectively safeguarding communications from eavesdropping. This letter highlights the potential of DL techniques to enhance communication security in complex multi-user environments.
{"title":"Secure Communication in Gaussian Multiple Access Wiretap Channels: A Deep Learning and Friendly Jamming Approach","authors":"Sankalp;Lata;Gaurang Sondur;Mahendra K. Shukla;Om Jee Pandey;Maxime Guillaud","doi":"10.1109/LNET.2025.3566243","DOIUrl":"https://doi.org/10.1109/LNET.2025.3566243","url":null,"abstract":"The use of deep learning (DL) in communication systems shows great promise, particularly through DL-based physical-layer techniques with autoencoders (AEs) for end-to-end learning. This letter presents an AE-based DL framework to enhance physical-layer security in scenarios where multiple transmitters communicate with the receiver under eavesdropping threats, specifically within a Gaussian multiple-access wiretap channel. A key feature is a friendly jammer that emits a high-power Gaussian signal to disrupt eavesdroppers. The proposed framework is particularly relevant for security-critical applications such as wireless health monitoring systems, where safeguarding sensitive data is paramount. We assess secrecy performance by analyzing the symbol error rate among users in the presence of both an eavesdropper and a jammer. Simulation results show that our DL-based Gaussian jamming strategy significantly improves secrecy performance, effectively safeguarding communications from eavesdropping. This letter highlights the potential of DL techniques to enhance communication security in complex multi-user environments.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"7 2","pages":"78-82"},"PeriodicalIF":0.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308550","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}
Pub Date : 2025-02-24DOI: 10.1109/LNET.2025.3545286
Alexandre Gemayel;Dimitrios Michael Manias;Abdallah Shami
As smart cities begin to materialize, the role of Unmanned Aerial Vehicles (UAVs) and their reliability becomes increasingly important. One aspect of reliability relates to Condition Monitoring (CM), where Machine Learning (ML) models are leveraged to identify abnormal and adverse conditions. Given the resource-constrained nature of next-generation edge networks, the utilization of precious network resources must be minimized. This letter explores the optimization of network resources for ML-based UAV CM frameworks. The developed framework uses experimental data and varies the feature extraction aggregation interval to optimize ML model selection. Additionally, by leveraging dimensionality reduction techniques, there is a 99.9% reduction in network resource consumption.
{"title":"Network Resource Optimization for ML-Based UAV Condition Monitoring With Vibration Analysis","authors":"Alexandre Gemayel;Dimitrios Michael Manias;Abdallah Shami","doi":"10.1109/LNET.2025.3545286","DOIUrl":"https://doi.org/10.1109/LNET.2025.3545286","url":null,"abstract":"As smart cities begin to materialize, the role of Unmanned Aerial Vehicles (UAVs) and their reliability becomes increasingly important. One aspect of reliability relates to Condition Monitoring (CM), where Machine Learning (ML) models are leveraged to identify abnormal and adverse conditions. Given the resource-constrained nature of next-generation edge networks, the utilization of precious network resources must be minimized. This letter explores the optimization of network resources for ML-based UAV CM frameworks. The developed framework uses experimental data and varies the feature extraction aggregation interval to optimize ML model selection. Additionally, by leveraging dimensionality reduction techniques, there is a 99.9% reduction in network resource consumption.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"7 2","pages":"108-112"},"PeriodicalIF":0.0,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308549","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}
Pub Date : 2025-02-17DOI: 10.1109/LNET.2025.3542762
Jian Song;Jing Li;Qingwang Wang;Yebo Gu;Tao Shen
Given the significant challenges of low resource utilization, load imbalance, and difficulties in meeting quality of service requirements in Flying Ad Hoc Networks (FANETs) routing protocols, this letter proposes a Graph Neural Network (GNN)-based approach for proximal policy optimization routing (GNNPPOR). The approach aims to integrate traffic engineering into FANETs to effectively distribute network load and meet quality of service requirements. In GNNPPOR, we design a GNN model that first aggregates multi-dimensional network state information efficiently through a message-passing mechanism. Subsequently, the network state is updated in real-time using a gated recurrent unit to adapt to dynamic changes in the FANETs network state. Finally, a multi-factor joint decision-making approach is proposed to identify suitable routes for each traffic based on the current network state. Simulation results demonstrate that GNNPPOR outperforms existing methods in several key metrics. Specifically, packet delivery rate increased by 25.3%, while energy consumption and network jitter decreased by 12.8% and 24.9%, respectively.
{"title":"GNNPPOR: A Proximal Policy Optimization Multi-Factor Joint Routing Approach Based on Graph Neural Networks in FANETs","authors":"Jian Song;Jing Li;Qingwang Wang;Yebo Gu;Tao Shen","doi":"10.1109/LNET.2025.3542762","DOIUrl":"https://doi.org/10.1109/LNET.2025.3542762","url":null,"abstract":"Given the significant challenges of low resource utilization, load imbalance, and difficulties in meeting quality of service requirements in Flying Ad Hoc Networks (FANETs) routing protocols, this letter proposes a Graph Neural Network (GNN)-based approach for proximal policy optimization routing (GNNPPOR). The approach aims to integrate traffic engineering into FANETs to effectively distribute network load and meet quality of service requirements. In GNNPPOR, we design a GNN model that first aggregates multi-dimensional network state information efficiently through a message-passing mechanism. Subsequently, the network state is updated in real-time using a gated recurrent unit to adapt to dynamic changes in the FANETs network state. Finally, a multi-factor joint decision-making approach is proposed to identify suitable routes for each traffic based on the current network state. Simulation results demonstrate that GNNPPOR outperforms existing methods in several key metrics. Specifically, packet delivery rate increased by 25.3%, while energy consumption and network jitter decreased by 12.8% and 24.9%, respectively.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"7 2","pages":"130-134"},"PeriodicalIF":0.0,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308552","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}
Due to the Context-aware responses, network behaviors simulation, and edge intelligence formulation, Generative Artificial Intelligence (GAI) has evolved rapidly. Firstly, this letter proposes a Convolutional Neural Network model based on GAI (CNN-GAI) to capture vehicle dynamic characteristics and complete Roadside Unit (RSU) deployment and task offloading decisions. Then, Attention Mechanism Reinforcement Learning (ARL) is used to achieve RSU-RSU Load-balancing. Finally, the load-balancing and utilization ratio of RSU are obtained by combining the model with the actual scenario.
{"title":"Generative AI-Enhanced Task Offloading Strategy for the IoV: An RSU-RSU Load-Balancing Perspective","authors":"Chao He;Wenhui Jiang;Xing Wang;Wanting Wang;Xin Xie","doi":"10.1109/LNET.2025.3542094","DOIUrl":"https://doi.org/10.1109/LNET.2025.3542094","url":null,"abstract":"Due to the Context-aware responses, network behaviors simulation, and edge intelligence formulation, Generative Artificial Intelligence (GAI) has evolved rapidly. Firstly, this letter proposes a Convolutional Neural Network model based on GAI (CNN-GAI) to capture vehicle dynamic characteristics and complete Roadside Unit (RSU) deployment and task offloading decisions. Then, Attention Mechanism Reinforcement Learning (ARL) is used to achieve RSU-RSU Load-balancing. Finally, the load-balancing and utilization ratio of RSU are obtained by combining the model with the actual scenario.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"7 3","pages":"161-165"},"PeriodicalIF":0.0,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145351898","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}
Pub Date : 2025-02-12DOI: 10.1109/LNET.2025.3541351
Masaki Oda;Akio Kawabata;Eiji Oki
This letter proposes two polynomial-time approximation algorithms for allocating servers to design a consistency-aware multi-server network for delay-sensitive applications. Each algorithm selects servers and determines the main-secondary server pairs to minimize the total delay. Previous work has not provided any polynomial-time algorithm. The proposed algorithms are theoretically guaranteed to output an approximate value within three times the optimal value. Numerical results show that the more computationally efficient of the two algorithms is 46.4 to $5.26 times 10^{4}$ times faster than an integer linear programming technique, while the maximum delay is, on average, merely 1.0196 times the optimal value.
{"title":"Approximation Polynomial-Time Algorithms for Consistency-Aware Multi-Server Network Design in Delay-Sensitive Applications","authors":"Masaki Oda;Akio Kawabata;Eiji Oki","doi":"10.1109/LNET.2025.3541351","DOIUrl":"https://doi.org/10.1109/LNET.2025.3541351","url":null,"abstract":"This letter proposes two polynomial-time approximation algorithms for allocating servers to design a consistency-aware multi-server network for delay-sensitive applications. Each algorithm selects servers and determines the main-secondary server pairs to minimize the total delay. Previous work has not provided any polynomial-time algorithm. The proposed algorithms are theoretically guaranteed to output an approximate value within three times the optimal value. Numerical results show that the more computationally efficient of the two algorithms is 46.4 to <inline-formula> <tex-math>$5.26 times 10^{4}$ </tex-math></inline-formula> times faster than an integer linear programming technique, while the maximum delay is, on average, merely 1.0196 times the optimal value.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"7 2","pages":"135-139"},"PeriodicalIF":0.0,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10883039","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：