2 papers
cs.CV2026
All Vehicles Can Lie: Efficient Adversarial Defense in Fully Untrusted-Vehicle Collaborative Perception via Pseudo-Random Bayesian Inference
Yi Yu, Libing Wu, Zhuangzhuang Zhang +3
Collaborative perception (CP) enables multiple vehicles to augment their individual perception capacities through the exchange of feature-level sensory data. However, this fusion m…
cs.CR2025
FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
Xinhai Yan, Libing Wu, Zhuangzhuang Zhang +3
Federated Learning (FL) enables collaborative model training while preserving data privacy, but it is highly vulnerable to backdoor attacks. Most existing defense methods in FL hav…