Zhi Jie Oh

Title: Innovations by Zhi Jie Oh in Artificial Intelligence Security

Introduction

Zhi Jie Oh is an innovative inventor based in Singapore, known for his contributions to the field of artificial intelligence security. With a focus on developing systems that enhance the security of generative artificial intelligence, he has made significant strides in this rapidly evolving domain.

Latest Patents

Zhi Jie Oh holds a patent for "Systems and methods for continuous self-improving artificial intelligence security." This invention provides a system and method for a continuous self-improving loop for the security of generative artificial intelligence (GenAI) deployed in a system. The process involves inputting prompts to a target GenAI to perform security tests. An attack vulnerability report can be generated based on the output produced by the target GenAI in response to various security tests. A validation module determines the accuracy of the data in the attack vulnerability report. For each security test that yields inaccurate output, a first dataset is generated to create new security tests. Conversely, for each accurate breach of security, a second dataset is created based on the respective security test that caused the breach. The target GenAI can then be updated by training it with this dataset to improve its security.

Career Highlights

Zhi Jie Oh is currently employed at Morgan Stanley Services Group Inc., where he applies his expertise in artificial intelligence and security. His work focuses on developing innovative solutions that address the challenges posed by evolving security threats in the digital landscape.

Collaborations

Zhi Jie Oh collaborates with talented professionals in his field, including Rongfeng Zhou and Fan Liu. These partnerships enhance the development of cutting-edge technologies and contribute to the advancement of artificial intelligence security.

Conclusion

Zhi Jie Oh's contributions to artificial intelligence security through his innovative patent demonstrate his commitment to improving the safety and reliability of generative AI systems. His work is paving the way for more secure applications in the future.