We call for original and unpublished papers, which must be formatted in the standard IEEE two-column format that is used by the INFOCOM 2025 main conference, and must not exceed six pages in length (including references). All submitted papers will go through a strict peer review process, and all accepted papers that are presented by one of the authors at the workshop will be published in the IEEE INFOCOM 2025 workshop proceedings and IEEE Xplore.
Please submit your papers in PDF format via edas https://edas.info/N33124 .
Submission Deadline: December 19, 2024 January 17, 2025
Notification of Acceptance: February 12, 2025
Camera Ready: February 26, 2025
Workshop: May 19, 2025
Deep learning has transformed many areas including the wireless domain. It has significantly unlocked the performance of wireless physical layer design, wireless sensing and wireless security. This workshop aims to bring together practitioners and researchers from both academia and industry for discussion and technical presentations on fundamental and practically relevant questions related to many challenges arising from deep learning for wireless communications, sensing and security. It also aims to provide the industry with fresh insight into the development of deep learning applications in wireless communication and networks.
In line with such objectives, original contributions, for both technical and demo sessions, are solicited on topics of interest to include, but not limited to, the following:
Deep learning for signal detection
Deep learning for channel modeling, estimation and prediction
Deep learning for resource optimization
Deep learning-based signal classification (including technology classification and modulation recognition)
Deep learning-based wireless sensing (including WiFi, mmWave radar, LoRa, RFID, etc)
Deep learning for localization and positioning
Deep learning for wireless security
Deep learning-based radio frequency fingerprint identification
Deep learning for physical layer security
Deep learning for wireless traffic analysis
Generative Models (e.g., LLM, Diffusion Models) for Wireless Data Synthesis
Large Language Models and Multi-modal Large Models for Wireless Communications, Sensing, and Security
Federated Learning for Wireless Communications, Sensing, and Security
AI-driven Digital Twins for Wireless Communications, Sensing, and Security
Explainable artificial intelligence for deep learning-based wireless communications, sensing, and security
Deep learning for emerging communication applications including intelligent reflection surface, unmanned aerial vehicles
Deep learning for new Internet of things applications
Adversarial attacks on deep learning-based wireless communication, sensing, and security
Professor Shiwen Mao, Auburn University, USA, smao@auburn.edu
Professor Yingying Chen, Rutgers University, USA, yingche@scarletmail.rutgers.edu
Professor Carlo Fischione, KTH Royal Institute of Technology, Sweden, carlofi@kth.se
Professor Jie Xu, The Chinese University of Hong Kong, Shenzhen, China. xujie@cuhk.edu.cn
Dr. Junqing Zhang, University of Liverpool, UK, junqing.zhang@liverpool.ac.uk
Dr. Xuyu Wang, Florida International University, USA, xuywang@fiu.edu
Dr. Francesca Meneghello, University of Padova, Italy. francesca.meneghello.1@unipd.it
Title: Optimal and Resilient Offloading in Collaborative DNN Inference
Jie Wu, Temple University, United States
Abstract
As Deep Neural Networks (DNNs) are widely used in various applications, including computer vision for image classification and object detection, it is crucial to reduce the makespan of DNN computation, especially when running on IoT devices. Offloading is a viable solution that shifts computation from slow IoT devices to a faster but remote cloud server. We first studied the optimal scheduling for one parallel-path DNN. Then, we extend the result to multiple line-structure DNNs. Heuristic results for general-structure DNNs, represented by Directed Acyclic Graphs (DAGs), are also discussed. However, one of the most critical challenges is offloading data via wireless networks, which are subject to dynamic channel conditions and high packet loss. We present RCNet, a Resilient Collaborative DNN inference framework designed to maintain high accuracy even under severe packet loss conditions. RCNet employs an unequal redundant encoding mechanism to prioritize the successful transmission of important features on IoT devices and utilizes a Transformer-based feature reconstruction module on the cloud to recover missing features efficiently. We implement a real-world testbed and conduct extensive experiments. The results demonstrate that RCNet can maintain accuracy in extremely harsh network conditions.
Bio
Jie Wu is Laura H. Carnell Professor at Temple University and the Director of the Center for Networked Computing (CNC). His current research interests include mobile computing and wireless networks, routing protocols, network trust and security, distributed algorithms, applied machine learning, and cloud computing. Dr. Wu regularly published in scholarly journals, conference proceedings, and books. He serves on several editorial boards, including IEEE/ACM Transactions on Networking and Journal of Computer Science and Technology. Dr. Wu is/was general chair/co-chair for IEEE IPDPS'23, ACM MobiHoc'23, and IEEE CCGrid 2024 as well as program chair/cochair for IEEE MASS’04, IEEE INFOCOM'11, and ICCCN’20. Dr. Wu is a Fellow of the AAAS and a Fellow of the IEEE. He is a Member of the Academia Europaea (MAE). He is on leave working as a Scientist at China Telecom.
Title: Toward (Truly) Resilient Computing and Communications in 6G Mobile Systems
Francesco Restuccia, Northeastern University, United States
Abstract: Sixth-generation (6G) mobile systems will extensively leverage artificial intelligence and machine learning algorithms (AI/ML) to implement a wide variety of inference and control tasks requiring ultra-low latency and near-perfect accuracy. While edge computing techniques can decrease the AI/ML computational burden of mobile devices, the required computing and communication performance goes far beyond what existing wireless technologies can deliver today. At the same time, it becomes of fundamental importance guaranteeing that both the AI/ML algorithms and the wireless network supporting the mobile system will be resilient by design to unforeseen events. In this seminar, we are going to present our recent research results on ensuring efficient and resilient computing and communications in the context of 6G mobile systems. We will conclude the seminar with discussions on ongoing research efforts and possible research directions.
Bio: Francesco Restuccia is an Assistant Professor in the Department of Electrical and Computer Engineering at Northeastern University. Dr. Restuccia’s main research focus is addressing the fundamental challenges related to edge-assisted data-driven resilient mobile systems. Restuccia’s research is funded by several grants from the National Science Foundation and the Department of Defense. Dr. Restuccia has received the ONR Young Investigator Award, the AFOSR Young Investigator Award, the ACM SIGMOBILE Research Highlights Award, the Mario Gerla Award in Computer Science, as well as best paper awards at IEEE INFOCOM and IEEE WOWMOM. Dr. Restuccia has been granted 12 US patents and has been cited 4700+ times with an h-index of 36. He regularly serves as a TPC member and reviewer for several top-tier ACM and IEEE conferences and serves in the editorial board of Computer Networks, IEEE Transactions on Cognitive Communications and Networking and IEEE Transactions on Mobile Computing. He is a Senior Member of IEEE and ACM.
08:30–08:40
08:40–10:00
RIS-Assisted MIMO Semantic Communication System for Speech Transmission
Weiqiang Tan (Guangzhou University, China); Lei Ling (GuangZhou University, China); Xianda Wu (South China Normal University, China); Jintao Wang (University of Macau, Macao); Yunfei Li (Anhui Polytechnic University, China); Chunguo Li (Southeast University, China)
LAMPS: Learning-based Mobility Planning via Posterior State Inference using Gaussian Cox Process Models
Egemen Erbayat, Yongsheng Mei and Gina Adam (The George Washington University, USA); Suresh Subramaniam (George Washington University, USA); Sean Coffey and Nathaniel D. Bastian (United States Military Academy, USA); Tian Lan (George Washington University, USA)
NERecon: Neural-Enhanced Reconciliation for Secure Physical Layer Key Generation
Aochen Jiao, Huanqi Yang and Weitao Xu (City University of Hong Kong, Hong Kong)
Adaptive Traffic Steering in Open RAN: Integrating Rule-Based Policies with Reinforcement Learning
Utkarsh Sharma (North Carolina State University, USA); Hua Wei (Arizona State University, USA); Jie Xu (University of Florida, USA); Mingzhe Chen (University of Miami, USA); Yuchen Liu (North Carolina State University, USA)
LECA-Net: A Context-Aware Local Enhancement Network for Massive MIMO CSI Feedback
Weiqiang Tan and Qiang Hua Chen (Guangzhou University, China); Jintao Wang (University of Macau, Macao); Zheng Shi (Jinan University, China); Chunguo Li (Southeast University, China)
10:00–10:30
10:30–11:30
Optimal and Resilient Offloading in Collaborative DNN Inference
Jie Wu (Temple University, United States)
11:30–12:34
UltraGSAttack: Targeted Adversarial Attack against Acoustic-based Gesture Recognition
Yunshu Wang, Yongpan Zou, Weiyu Chen, Feihang Dong and Yanbo He (Shenzhen University, China); Kaishun Wu (The Hong Kong University of Science and Technology, China)
Energy-Efficient SLAM via Joint Design of Sensing, Communication, and Exploration Speed
Zidong Han (Southern University of Science and Technology); Ruibo Jin (Sustech, China); Xiaoyang Li (Shenzhen Research Institute of Big Data, China); Bingpeng Zhou (Sun Yat-sen University, China); Qinyu Zhang (Shenzhen Graduate School, Harbin Institute of Technology, China); Yi Gong (Southern University of Science and Technology, Shenzhen, China)
A Gaussian Splatting Approach to Continuous Radio Map Construction
Anthony Chen and Shiwen Mao (Auburn University, USA); Zhu Li (University of Missouri, Kansas City, USA & USAF Academy, USA); Hongliang Zhang (Peking University, China); Dusit Niyato (Nanyang Technological University, Singapore); Zhu Han (University of Houston, USA)
Channel Matters: Exploring LoS/NLoS Channel Effects on WiFi Sensing Performance
Md Nafeez Fahad and Eyuphan Bulut (Virginia Commonwealth University, USA)
12:30 – 14:00
14:00–15:00
Toward (Truly) Resilient Computing and Communications in 6G Mobile Systems
Francesco Restuccia (Northeastern University, United States)
15:00–15:32
LLMKey: LLM-Powered Wireless Key Generation Scheme for Next-Gen IoV Systems
Huanqi Yang and Weitao Xu (City University of Hong Kong, Hong Kong)
IoVSL: An IoV Anomaly Detection Method Using Split Learning with the Open-Source Large Language Model
Jinhui Cao, Xiaoqiang Di, Hui Qi, Jinqing Li and Huamin Yang (Changchun University of Science and Technology, China); Pengfei Hu (Shandong University, China); Liang Zhao (Shenyang Aerospace University, China)
15:30–16:00
16:00–17:06
Radio Fingerprinting of Wi-Fi Devices Through MIMO Compressed Channel Feedback
Francesca Meneghello (University of Padova, Italy); Khandaker Foysal Haque and Francesco Restuccia (Northeastern University, USA)
Optic Fingerprint(OFP): Enhancing Security in Li-Fi Network
Ziqi Liu (Institut Superieur d Electronique de Paris, France); Xuanbang Chen (Nanchang University, China); Xun Zhang (Institut Superieur d Electronique de Paris, France)
Jamming Echoes: On the Impact of Out-of-Band Interference on Radio Frequency Fingerprinting
Ingrid Huso (Politecnico di Bari, Italy & CNIT, Italy); Salvatore Carbonara (Politecnico di Bari, Italy); Savio Sciancalepore (Eindhoven University of Technology (TU/E), The Netherlands); Gabriele Oligeri (Hamad Bin Khalifa University, Qatar); Giuseppe Piro and Gennaro Boggia (Politecnico di Bari, Italy)
An Investigation of Power Amplifier Feature for Deep Learning Based RF Fingerprint Identification
Wentao Jing and Linning Peng (Southeast University, China); Junqing Zhang (University of Liverpool, United Kingdom (Great Britain)); Hua FU (Southeast University, China)
17:07–17:55
CanFormer Based Channel Prediction for Robotic Body Area Networks
Keyan Li (Institute of Computing Technology, China); Congcong Wang (Institute of Computing, China); Jinglin Shi (Chinese Academy of Sciences, China); Yiqing Zhou (Chinese Academy of Science, China); Zhang Cheng (University of Chinese Academy Sciences, China)
Deep Learning-based mmWave MIMO Channel Estimation using sub-6 GHz Channel Information: CNN and UNet Approaches
Faruk Pasic (TU Wien, Austria); Lukas Eller (Vienna University of Technology, Austria); Stefan Schwarz, Markus Rupp and Christoph F Mecklenbräuker (TU Wien, Austria)
NeRF-APT: A New NeRF Framework for Wireless Channel Prediction
Jingzhou Shen, Tianya Zhao, Yanzhao Wu and Xuyu Wang (Florida International University, USA)
17:55 – 18:00