Steeple Claydon, United Kingdom

Thomas Bonner

USPTO Granted Patents = 1 

Average Co-Inventor Count = 6.0

ph-index = 1


Company Filing History:


Years Active: 2025

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Thomas Bonner - Innovator in Machine Learning Threat Detection

Introduction

Thomas Bonner is a notable inventor based in Steeple Claydon, GB. He has made significant contributions to the field of machine learning, particularly in the area of threat detection. His innovative approach aims to enhance the security of machine learning models, ensuring they operate safely and effectively.

Latest Patents

Thomas Bonner holds a patent for a groundbreaking invention titled "Scanning and Detecting Threats in Machine Learning Models." This patent describes a method for scanning machine learning models to identify actual or potential threats. The detection process can occur before the execution of the model or within an isolated execution environment. The system performs various checks, including a machine learning file format check, vulnerability check, tamper check, and stenography check. Additionally, the model is monitored during execution to ensure its integrity. After scanning, the system generates a signature based on the detected threats.

Career Highlights

Thomas Bonner is currently employed at Hiddenlayer, Inc., where he continues to develop innovative solutions in the realm of machine learning. His work focuses on enhancing the security and reliability of machine learning applications, making significant strides in the industry.

Collaborations

Some of Thomas's coworkers include Tanner Burns and Chris Sestito, who contribute to the collaborative environment at Hiddenlayer, Inc. Their combined expertise fosters innovation and drives the development of advanced technologies.

Conclusion

Thomas Bonner's contributions to machine learning threat detection exemplify the importance of innovation in technology. His patent and ongoing work at Hiddenlayer, Inc. highlight his commitment to enhancing the security of machine learning models.

This text is generated by artificial intelligence and may not be accurate.
Please report any incorrect information to support@idiyas.com
Loading…