The paper reveals that intermediate representations in vertical federated learning retain exploitable geometric structure, and introduces VENOM—a geometry‑aware model‑stealing framework that outperforms existing defenses across multiple datasets, even under distribution shift.
This paper introduces FedMix, a method that enhances vertical federated learning by mixing aligned and unaligned data, theoretically demonstrating the value of unaligned data and empirically achieving over 10% ROI improvement and significant AUC gains while keeping computational and communication overhead low.
This article examines the challenges of data privacy in big‑data environments and presents a comprehensive approach to vertical federated learning, detailing framework optimizations, Paillier homomorphic encryption enhancements, PSI‑based feature selection, and adversarial learning techniques to improve model stability and deployment on a unified ML platform.
