Yang Pan

TL;DR: This paper proposes a novel privacy-preserving personalized federated learning framework that supports heterogeneous model architectures and sizes, utilizing participants' knowledge to cluster similar data distributions and guaranteeing privacy through ring aggregation and cross-cluster knowledge transfer.

TL;DR: Zhang et al. as discussed by the authors proposed a novel federated learning framework with user-level personalized privacy protection (FLUP) to meet the personalized privacy requirements of different users while maintaining high data utility.

TL;DR: This survey introduces the Internet of Agents (IoA) framework, enabling seamless interconnection and collaboration among heterogeneous AI agents, and discusses its architecture, operational enablers, and emerging applications, while highlighting open research directions for resilient and trustworthy IoA ecosystems.

TL;DR: TRACEGADGET proposes a federal provenance graph-based framework for detecting and tracing network-level APT attacks, efficiently revealing lateral movement attacks through host interactions, achieving 100% APT path reconstruction with high robustness in experiments with real APT attack datasets.