Guijuan Wang

Closed-loop semantic–visual adaptation for identity-preserving personalized image generation

Lattice-Based Standardized Cross-Chain Payment Protocol for Post-Quantum IoT Ecosystems

A lattice-based standardized cross-chain payment protocol designed for post-quantum security and lightweight deployment, that employs a provably secure lattice signature scheme and a lightweight interoperability framework to automate cross-chain coordination.

FedDyna: Privacy-Preserving Federated Learning with Dynamic Noise Adaptation and Structural Bias Alignment for Non-IID Environments

FedDyna is proposed, a novel framework that uses an adaptive noise injection mechanism to enhance privacy in non-IID data environments and effectively demonstrates the significant divergence between dynamic and static noise under non-IID settings.

Defending Against Backdoor Attacks via Alignment Checking in Model-Contrastive Federated Learning

FedDAB, a two-phase method that combines local contrastive regularization with alignment checking, to defend against backdoor attacks, is proposed and theoretically proves FedDAB's robustness with a convergence rate of $\mathcal{O}(1/T)$.