Mingjie Sun

Title: The Innovative Mind of Mingjie Sun

Introduction

Mingjie Sun is a prominent inventor based in Pittsburgh, PA. He has made significant contributions to the field of machine learning and artificial intelligence. His work focuses on developing methods to enhance the security and reliability of machine learning systems.

Latest Patents

Mingjie Sun holds a patent titled "Method and system for breaking backdoored classifiers through adversarial examples." This innovative patent describes a computer-implemented method for training a machine learning network. The method includes receiving input data from one or more sensors, selecting batch samples that include perturbed samples from a source class, and identifying these perturbed samples. The process also involves determining a trigger event in response to a trigger pattern, which induces a pre-determined response on a classifier. Ultimately, the method outputs a classification based on the identified trigger pattern and extracts a set of trigger patterns from the machine-learning network. This patent showcases his expertise in addressing vulnerabilities in machine learning classifiers.

Career Highlights

Mingjie Sun is currently employed at Robert Bosch GmbH, where he applies his knowledge and skills to advance technology in the field. His work at Bosch allows him to collaborate with other talented professionals and contribute to innovative projects that have a real-world impact.

Collaborations

Mingjie has worked alongside notable colleagues such as Jeremy Zico Kolter and Filipe J Cabrita Condessa. These collaborations have fostered a creative environment that encourages the exchange of ideas and the development of cutting-edge solutions.

Conclusion

Mingjie Sun is a dedicated inventor whose work in machine learning is paving the way for more secure and efficient systems. His contributions, particularly through his patent, highlight his commitment to innovation and excellence in technology.