Hong Zhao

Sneakdoor introduces a novel backdoor attack method that enhances stealthiness in dataset condensation by using a generative module to create input-aware triggers, achieving high attack efficacy while remaining imperceptible.

FedIDM introduces a novel federated learning framework that uses iterative distribution matching to achieve fast and stable convergence and maintain high model utility even when facing a large proportion of Byzantine malicious clients.

CodeCytos is a novel coding-based reasoning agent framework that enables dynamic, programmable interaction with spatial molecular imaging data, significantly improving the automation and customization of complex tissue analysis.

The paper proposes Shallow-RHS, an asymmetric graph-completion model, to solve the cold-start problem for both new content and new devices in large-scale recommendation systems.