Gaurang Sriramanan

About

Gaurang Sriramanan is a researcher advancing the frontiers of adversarial machine learning, with a primary focus on fortifying deep neural networks against malicious perturbations. His key research areas include adversarial robustness, defensive mechanisms for neural networks, and feature-level stochastic smoothing. Sriramanan’s major contribution, detailed in his highly cited 2021 paper “Boosting Adversarial Robustness using Feature Level Stochastic Smoothing,” introduces a novel defense strategy that enhances model resilience by applying stochastic smoothing at the feature level, rather than solely at the input layer. This work addresses the critical gap between current state-of-the-art defenses and the stringent robustness requirements for safety-critical applications like robotics and autonomous navigation. With 4 citations, this paper has already garnered attention for its innovative approach to improving robust accuracy. Sriramanan’s research is particularly notable for its practical implications, aiming to bridge the divide between theoretical adversarial defenses and real-world deployment in high-stakes environments. His work continues to influence the development of more reliable and secure AI systems, making him a promising voice in the ongoing effort to build trustworthy deep learning models.

Research Focus

Key Achievements

Top Papers

1. 1
   Boosting Adversarial Robustness using Feature Level Stochastic Smoothing

   4 citations · 2021

Key Collaborators

Contact & Links