The Fifth Workshop on Machine Learning and Deep Learning for Wireless Security 

Submission Instruction

We call for original and unpublished papers, which must be formatted in the standard IEEE two-column format that is used by the IEEE ICC 2026 main conference, and must not exceed six pages in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 ICC 2026 workshop proceedings and IEEE Xplore. 

Please submit your papers in PDF format via edas: https://edas.info/newPaper.php?c=34795

Important Dates

• Paper submission deadline: 18 January 2026 31 January 2026

• Notification of acceptance: 8 March 2026

• Camera-ready papers: 15 March 2026

• Workshop date: to be confirmed

Workshop Scope

Deep learning has transformed many areas including the wireless security and privacy domains. It has significantly strengthened the design of security approaches, attacks as well as the defence to the Internet of Things (IoT), beyond 5G/6G, from the physical layer to the upper layers. 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-based security and privacy for wireless communications and networking. It also aims to provide the industry with fresh insight into the development of machine learning and deep learning applications in wireless security. 

Topics of Interests

In line with such objectives, original contributions are solicited on topics of interest to include, but not limited to, the following: 

• Artificial intelligence-generated content (AIGC) for wireless security 

• Large language model (LLM) for wireless security 

• Machine learning/deep learning-driven device identification using radio frequency fingerprint, physical layer channel features, and network traffic features 

• Deep learning-enhanced physical layer security 

• Deep learning-enhanced RF security 

• Adversarial machine learning in wireless communications, including adversarial erosion attacks, poisoning attacks, and Trajon/backdoor attacks 

• Defensive and anticipatory aspects of adversarial machine learning in wireless communications 

• Security and privacy of deep learning-based wireless sensing 

• Intrusion and anomaly detection for wireless networks 

• Prototype, practical testbeds, and performance evaluation 

Organization Team

Steering Committee

General Chairs

TPC Chairs

Programs

Session 1: Device Fingerprinting and Authentication  (08:30 – 09:10)

Security Assessment of Deep Learning-Based RF Fingerprinting for Wireless IoT Standards

Cross-DMRS RF Fingerprint Identification for LTE-V2X Using Autocorrelation Features

Impairment Leakage Attention-Based Denoising for 5G NR RF Fingerprinting Under Low SNR

Incremental Learning-Based Open-Set Classification of Unknown UAVs via RF Signal Semantics

Session 2: Physical Layer Security: RIS and Covert Transmission  (09:10 – 10:00)

Discriminative Siamese Learning for Pilot Spoofing Attack Detection in MIMO Uplink Systems

Secrecy-Aware Beamforming Optimization in RIS-Assisted MIMO Systems Using SAC DRL

Secure NOMA-Enabled Aerial RIS Networks via Multi-Agent Multi-Stage Curriculum Learning

Generative AI Based Secrecy Throughput Improvement in IRS-NOMA-Aided FANETs

Hiding Information Under Overt Signals: A Partially Covert Communication Framework Based on GANs

Session 3: Jamming Detection and Wireless Defense  (10:30 – 11:30)

Deep Unfolding Supported Cell-Free Anti-Jamming Coordinated Multipoint Beam Pattern Synthesis

Jamming Recognition for OFDM Signals: FedProx-Based Quality-Aware Client Selection

Multi-Agent Deep Reinforcement Learning for Collaborative UAV Relay Networks Under Jamming Attacks

Explainable and Hardware-Efficient Jamming Detection for 5G Networks Using the Convolutional Tsetlin Machine

Dynamic Security Resource Allocation in V2X Edge Computing via Attention-BiGAN and DRL

Buffer-Guided Online Intrusion Detection Under Dynamic Wireless Traffic

Session 4: Network Security and Traffic Analysis  (11:30 – 12:30)

Emulation Digital Twin Framework: Case Study on NGAP Attacks in 5G Control Plane

Physical Layer Message Prediction for 5G Radio Access Network Protocols

Application-Aware Traffic Switching Between 5G and Wi-Fi (and Beyond) for High-Throughput Services

G2FL: Robust Federated Learning for GNSS Spoofing Detection

Payload Based Multi-Phase Deep Learning for Encrypted Traffic Classification

Adversarial ML for Channel-Based Key Agreement for Underwater Acoustic Communications