8 papers
Robust Driving Control for Autonomous Vehicles: An Intelligent General-sum Constrained Adversarial Reinforcement Learning Approach
Junchao Fan, Qi Wei, Ruichen Zhang +4
Deep reinforcement learning (DRL) has demonstrated remarkable success in developing autonomous driving policies. However, its vulnerability to adversarial attacks remains a critica…
Efficient and High-Accuracy Private CNN Inference with Helper-Assisted Malicious Security
Kaiwen Wang, Xiaolin Chang, Junchao Fan +1
Machine Learning as a Service (MLaaS) exposes sensitive client data to service providers. Private inference mitigates this risk while preserving model functionality. Despite extens…
Sparse Threats, Focused Defense: Criticality-Aware Robust Reinforcement Learning for Safe Autonomous Driving
Qi Wei, Junchao Fan, Zhao Yang +3
Reinforcement learning (RL) has shown considerable potential in autonomous driving (AD), yet its vulnerability to perturbations remains a critical barrier to real-world deployment.…
Safe and Economical UAV Trajectory Planning in Low-Altitude Airspace: A Hybrid DRL-LLM Approach with Compliance Awareness
Yanwei Gong, Junchao Fan, Ruichen Zhang +3
The rapid growth of the low-altitude economy has driven the widespread adoption of unmanned aerial vehicles (UAVs). This growing deployment presents new challenges for UAV trajecto…
Towards Reliable Service Provisioning for Dynamic UAV Clusters in Low-Altitude Economy Networks
Yanwei Gong, Ruichen Zhang, Xiaoqing Wang +5
Unmanned Aerial Vehicle (UAV) cluster services are crucial for promoting the low-altitude economy by enabling scalable, flexible, and adaptive aerial networks. To meet diverse serv…
DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences
Bocheng Ju, Junchao Fan, Jiaqi Liu +1
Federated learning enables collaborative machine learning while preserving data privacy. However, the rise of federated unlearning, designed to allow clients to erase their data fr…