Deevashwer Rathee

Title: Deevashwer Rathee: Innovator in Secure Machine Learning

Introduction

Deevashwer Rathee is a prominent inventor based in Panchkula, India. He has made significant contributions to the field of machine learning, particularly in enhancing the security of deep neural networks. His innovative approach focuses on privacy-preserving techniques that are crucial in today's data-driven world.

Latest Patents

Deevashwer Rathee holds a patent for "Private inference in deep neural network." This invention provides a secure inference method over Deep Neural Networks (DNNs) using secure two-party computation. The technique allows for privacy-preserving machine learning by employing a specific type of comparison that can be utilized as a building block for various layers in the DNN, including ReLU activations and divisions. The secure inference computes a Boolean share of a bit that indicates whether input value x is less than input value y, where x is held by a user and y is held by a provider of the DNN. This method is more efficient than traditional approaches, as it parses inputs into leaf strings of multiple bits, making it better suited for complex DNNs.

Career Highlights

Deevashwer Rathee is currently associated with Microsoft Technology Licensing, LLC, where he continues to innovate in the field of machine learning. His work is instrumental in advancing secure computing methods that protect user privacy while leveraging the power of deep learning technologies.

Collaborations

Deevashwer has collaborated with talented individuals such as Nishanth Chandran and Divya Gupta. Their combined expertise contributes to the development of cutting-edge technologies in the realm of secure machine learning.

Conclusion

Deevashwer Rathee's contributions to secure machine learning through his innovative patent demonstrate his commitment to advancing technology while prioritizing user privacy. His work is paving the way for more secure applications of deep neural networks in various industries.