Publications

My research focuses on machine learning security, particularly in the areas of model extraction and adversarial machine learning.

Conference

Army of Thieves: Enhancing Black-Box Model Extraction via Ensemble-based Sample Selection

Akshit Jindal, Vikram Goyal, Saket Anand, Chetan Arora

WACV 20242024

We propose a novel approach to enhance the effectiveness of black-box model extraction attacks using ensemble-based sample selection strategies...

PDFCode
Patent

Method and system for assigning unique voice for electronic device

Sourabh Tiwari, Akshit Jindal, Saksham Goyal, Vinay Vasanth Patage, Ravibhushan B Tayshete

US Patent Office2022

A novel method for generating and assigning unique voice characteristics to electronic devices...

PDF