Location History:
- San Francisco, CA (US) (2020)
- Los Angeles, CA (US) (2020 - 2024)
Company Filing History:
Years Active: 2020-2024
Title: Innovations of Neil Serebryany
Introduction
Neil Serebryany is a prominent inventor based in Los Angeles, California. He has made significant contributions to the field of machine learning and artificial intelligence. With a total of four patents to his name, Serebryany is recognized for his innovative approaches to enhancing the robustness and security of machine learning models.
Latest Patents
One of Serebryany's latest patents is focused on the robustness characterization of machine learning models. This invention involves receiving a file with a known classification and selecting a perturbation algorithm to modify the file. The goal is to create a sequence of actions that leads the machine learning model to provide a desired classification. The process includes iteratively modifying the file until the model outputs a known second classification.
Another notable patent is the artificial intelligence adversarial vulnerability audit tool. This tool receives an image with a known classification and iteratively modifies it using a perturbation algorithm. The modified images are then input into the machine learning model until a different classification is produced. The data characterizing these modifications can be displayed, stored, or transmitted, providing valuable insights into the model's vulnerabilities.
Career Highlights
Serebryany currently works at Calypso AI Corp, where he continues to develop innovative solutions in the field of artificial intelligence. His work focuses on enhancing the security and reliability of machine learning systems, making significant strides in the industry.
Collaborations
Serebryany collaborates with talented individuals such as Victor Ardulov and David Richard Gibian. Their combined expertise contributes to the advancement of technology in their respective fields.
Conclusion
Neil Serebryany is a notable inventor whose work in machine learning and artificial intelligence has led to significant advancements in the field. His innovative patents reflect his commitment to improving the robustness and security of machine learning models.