activity
20132022
most citedOn the Origin of Deep Learning

88 citations · 204 across the 28 of their papers we have counts for

collaborators
Showing cs.LGShow all

11 papers · 1 filter

cs.LG20221 cited

Watch What You Pretrain For: Targeted, Transferable Adversarial Examples on Self-Supervised Speech Recognition models

Raphael Olivier, Hadi Abdullah, Bhiksha Raj

A targeted adversarial attack produces audio samples that can force an Automatic Speech Recognition (ASR) system to output attacker-chosen text. To exploit ASR models in real-world…

cs.LG20211 cited

Training image classifiers using Semi-Weak Label Data

Anxiang Zhang, Ankit Shah, Bhiksha Raj

In Multiple Instance learning (MIL), weak labels are provided at the bag level with only presence/absence information known. However, there is a considerable gap in performance in…

cs.LG2021

Constant Random Perturbations Provide Adversarial Robustness with Minimal Effect on Accuracy

Bronya Roni Chernyak, Bhiksha Raj, Tamir Hazan +1

This paper proposes an attack-independent (non-adversarial training) technique for improving adversarial robustness of neural network models, with minimal loss of standard accuracy…

cs.LG2020

Exploiting Non-Linear Redundancy for Neural Model Compression

Muhammad A. Shah, Raphael Olivier, Bhiksha Raj

Deploying deep learning models, comprising of non-linear combination of millions, even billions, of parameters is challenging given the memory, power and compute constraints of the…

cs.LG20191 cited

Non-Determinism in Neural Networks for Adversarial Robustness

Daanish Ali Khan, Linhong Li, Ninghao Sha +4

Recent breakthroughs in the field of deep learning have led to advancements in a broad spectrum of tasks in computer vision, audio processing, natural language processing and other…

cs.LG20193 cited

Nonlinear Semi-Parametric Models for Survival Analysis

Chirag Nagpal, Rohan Sangave, Amit Chahar +3

Semi-parametric survival analysis methods like the Cox Proportional Hazards (CPH) regression (Cox, 1972) are a popular approach for survival analysis. These methods involve fitting…