Su Yao
Papers
1
Total Citations
7
H-Index
1
About
Dr. Su Yao is a leading researcher at the intersection of artificial intelligence security and the Internet of Robotic Things (IoRT), with a primary focus on safeguarding large vision language models (LVLMs) against emerging cyber threats. In their seminal 2024 work, "SecFFT: Safeguarding Federated Fine-Tuning for Large Vision Language Models Against Covert Backdoor Attacks in IoRT Networks," Dr. Yao addresses a critical vulnerability in federated learning environments where malicious actors can implant hidden backdoors during model fine-tuning. This research, already garnering 7 citations shortly after publication, proposes a novel defense mechanism that preserves model utility while neutralizing covert attacks—a breakthrough for deploying LVLMs in sensitive IoRT applications like smart cities, power grids, and autonomous transportation. Dr. Yao's contributions are particularly notable for bridging the gap between theoretical AI security and practical robotic systems, ensuring that visual perception and understanding—the foundational elements of modern embodied intelligence—remain trustworthy. Their work is essential reading for researchers developing secure, real-world AI systems where safety and reliability are paramount.
Research Focus
Key Achievements
Top Papers
- 1