Ming Zhao

This paper argues that much of the existing research on Federated Learning (FL) security is based on idealized assumptions, and provides a practical evaluation framework showing that real-world attack performance is often less severe and more unstable than predicted.

The paper introduces PhishEye, a fully dynamic self-supervised system that models Ethereum transactions as a heterogeneous temporal attributed multi-graph and uses temporal graph contrastive learning to achieve high accuracy in detecting phishing activities.

WATSON is a novel, efficient shadow stack protection mechanism for embedded systems that utilizes standard hardware data watchpoints to mitigate control-flow hijacking vulnerabilities without relying on specialized hardware extensions.

The paper introduces FIDO, a novel framework that significantly boosts firmware fuzzing efficiency by accurately managing the timing and quantity of input delivery based on the firmware's internal input availability checks.

PropLLM introduces a novel propagation-aware framework that uses LLMs and hop-by-hop scene reconstruction to accurately localize root causes and determine fault types in complex network fault diagnosis, significantly outperforming existing methods.

The paper introduces PRISM, a novel representation learning framework that learns isometric embeddings by explicitly modeling the intrinsic geodesic metric of 3D surfaces, achieving superior performance on various geometric tasks.