Sizhe Huang

About

Sizhe Huang is a leading researcher at the intersection of artificial intelligence, cybersecurity, and the Internet of Robotic Things (IoRT). His work focuses on safeguarding federated learning systems in heterogeneous, cross-silo environments, where massive robotic networks collaborate on sensitive data. Huang’s major contributions include pioneering the application of Moving Target Defense (MTD) to protect privacy and integrity in IoRT—a novel approach that dynamically shifts attack surfaces to thwart adversaries. His most-cited paper, “Safeguarding Privacy and Integrity of Federated Learning in Heterogeneous Cross-Silo IoRT Environments: A Moving Target Defense Approach” (2024), has already garnered 14 citations, reflecting its immediate impact on securing smart factories, power grids, and transportation systems. In another influential work, “SecFFT: Safeguarding Federated Fine-Tuning for Large Vision Language Models Against Covert Backdoor Attacks in IoRT Networks” (2024, 7 citations), Huang addresses emerging threats to large vision-language models (LVLMs) in embodied robotic networks. His research is vital for enabling trustworthy AI in critical infrastructure, where visual perception and collaborative learning must resist covert attacks. Huang’s innovative fusion of cybersecurity and federated learning positions him as a key figure in building resilient, privacy-preserving IoRT ecosystems.

Research Focus

Key Achievements

Top Papers

1. 1
   Safeguarding Privacy and Integrity of Federated Learning in Heterogeneous Cross-Silo IoRT Environments: A Moving Target Defense Approach

   14 citations · 2024
2. 2
   SecFFT: Safeguarding Federated Fine-Tuning for Large Vision Language Models Against Covert Backdoor Attacks in IoRT Networks

   7 citations · 2024

Key Collaborators

Contact & Links