Kuan Huang
Papers
1
Total Citations
1
H-Index
1
About
Kuan Huang is a leading researcher at the intersection of computer vision, mobile computing, and system security. Their work focuses on enabling efficient and secure deployment of deep neural networks (DNNs) for critical real-world applications, including autonomous driving, UAV navigation, and robotics. Huang’s most notable contribution is the development of EffTEE, a framework that achieves efficient image classification and object detection on mobile devices by leveraging Trusted Execution Environments (TEEs). This work addresses the fundamental challenge of protecting sensitive input data while maintaining high performance on resource-constrained platforms. Although a relatively recent publication, EffTEE has already garnered early citations, signaling its potential impact on secure mobile AI. Huang’s research is distinguished by its practical focus on bridging the gap between advanced DNN capabilities and the security demands of edge deployment. Their work is particularly relevant for students and researchers interested in building trustworthy AI systems for safety-critical applications, where both accuracy and data protection are paramount.
Research Focus
Key Achievements
Top Papers
- 1