2 papers
cs.LG2022
Scoring Black-Box Models for Adversarial Robustness
Jian Vora, Pranay Reddy Samala
Deep neural networks are susceptible to adversarial inputs and various methods have been proposed to defend these models against adversarial attacks under different perturbation mo…
cs.SD2021
SpliceOut: A Simple and Efficient Audio Augmentation Method
Arjit Jain, Pranay Reddy Samala, Deepak Mittal +2
Time masking has become a de facto augmentation technique for speech and audio tasks, including automatic speech recognition (ASR) and audio classification, most notably as a part…