Zhili Zhang
Papers
2
Total Citations
66
H-Index
2
About
Zhili Zhang is a leading researcher at the intersection of privacy-preserving machine learning, deep learning, and the Internet of Things (IoT), with a particular focus on securing robotic systems. Their work addresses a critical challenge: how to harness the power of deep learning for image classification and other tasks in industrial IoT and robotics without compromising sensitive data. Zhang’s major contributions include pioneering privacy-preserving deep learning models for robot systems, such as the "Privacy-preserving image multi-classification deep learning model" (38 citations) and the "PDLHR" framework with homomorphic re-encryption (28 citations). These innovations enable robots to leverage massive datasets for advanced feature extraction while ensuring data confidentiality through cryptographic techniques. By tackling the tension between data utility and privacy in real-world applications, Zhang has laid foundational groundwork for secure, intelligent automation. Their work is particularly notable for its practical relevance to Industry 4.0, where robot systems are increasingly deployed but face stringent privacy regulations. With a growing citation impact, Zhili Zhang is shaping the future of trustworthy AI in critical infrastructure.
Research Focus
Key Achievements
Top Papers
- 1
- 2