Woo Jae Kim

Title: Woo Jae Kim: Innovator in Adversarial Robustness

Introduction

Woo Jae Kim is a prominent inventor based in Daejeon, South Korea. He has made significant contributions to the field of adversarial robustness through his innovative methods and systems. His work focuses on enhancing the reliability of machine learning models against adversarial attacks.

Latest Patents

Woo Jae Kim holds a patent for a "Method and system for separating and recalibrating feature for adversarial robustness." This patent discloses a method that involves disentangling an input feature map into a robust feature and a non-robust feature based on a robustness score. The process includes generating a recalibrated feature by adjusting the activation of the non-robust feature and combining it with the robust feature to create an output feature map. He has 1 patent to his name.

Career Highlights

Woo Jae Kim is affiliated with the Korea Advanced Institute of Science and Technology, where he continues to push the boundaries of research in his field. His work has garnered attention for its potential applications in improving the security of artificial intelligence systems.

Collaborations

Some of his notable coworkers include Sung-Eui Yoon and Yoonki Cho, who have collaborated with him on various projects related to adversarial robustness.

Conclusion

Woo Jae Kim's innovative approach to adversarial robustness positions him as a key figure in the field of machine learning. His contributions are paving the way for more secure AI systems in the future.