Yushi Cheng

Title: Yushi Cheng: Innovator in Image Adversarial Examples

Introduction

Yushi Cheng is a prominent inventor based in Hangzhou, China. He has made significant contributions to the field of machine vision through his innovative patent. His work focuses on generating image adversarial examples, which have important implications for deep learning algorithms.

Latest Patents

Yushi Cheng holds a patent titled "Method and system for generating image adversarial examples based on an acoustic wave." This patent describes a method that involves acquiring an image containing a target object or scene. The process includes generating simulated image examples that have adversarial effects on a deep learning algorithm within a target machine vision system. The optimization of these generated examples leads to the creation of an optimal adversarial example and corresponding parameters. These parameters are then injected into an inertial sensor of the target machine vision system using an acoustic wave, resulting in specific blurry patterns in real-world images.

Career Highlights

Yushi Cheng is affiliated with Zhejiang University, where he continues to advance his research and innovation in the field of machine vision. His work has garnered attention for its potential applications in enhancing the robustness of machine learning systems.

Collaborations

Yushi Cheng collaborates with notable colleagues, including Xiaoyu Ji and Wenyuan Xu. Their combined expertise contributes to the advancement of research in image processing and machine learning.

Conclusion

Yushi Cheng's innovative work in generating image adversarial examples showcases his significant contributions to the field of machine vision. His patent reflects a deep understanding of the intersection between acoustic waves and image processing, paving the way for future advancements in technology.