Jingfeng Zhang

Jingfeng Zhang is a researcher at RIKEN Advanced Intelligence Project (RIKEN-AIP) working in the "Imperfect Information Learning Team" supervised by Prof. Masashi Sugiyama. Prior to RIKEN-AIP, he obtained his Ph.D. in 2020 from the School of Computing at the National University of Singapore under Prof. Mohan Kankanhalli, and his Bachelor's degree in 2016 from Taishan College at Shandong University, China.

Dr. Zhang specializes in adversarial robustness in AI systems, focusing on making artificial intelligence safe for human beings. His research investigates how standard trained models fail when confronted with adversarial examples and develops methods to enhance model reliability through adversarial training. Key aspects of his work include:

• Developing techniques to make decision boundaries "thick" in machine learning models
• Simulating adversarial attacks during training to improve robustness
• Evaluating and enhancing reliability of AI-powered tools
• Addressing security vulnerabilities in deep learning systems

Dr. Zhang has received significant recognition for his work through competitive funding and awards:

• Strategic Basic Research Programs ACT-X 2021-2023 funding
• JSPS Grants-in-Aid for Scientific Research (KAKENHI), Early-Career Scientists 2022-2023
• RIKEN Ohbu Award 2022

He actively contributes to the machine learning community as a reviewer for top-tier conferences including ICLR, ICML, and NeurIPS. Dr. Zhang has presented his research at international venues such as the EPFL Center for Intelligent Systems, where he delivered talks on adversarial robustness in 2022 and 2023, demonstrating the practical applications of his theoretical work in real-world AI systems.