Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Bhavya Kailkhura

Mixture of Robust Experts (MoRE): A Flexible Defense Against Multiple Perturbations


Apr 21, 2021
Hao Cheng, Kaidi Xu, Chenan Wang, Xue Lin, Bhavya Kailkhura, Ryan Goldhahn


  Access Paper or Ask Questions

Certifiably-Robust Federated Adversarial Learning via Randomized Smoothing


Mar 30, 2021
Cheng Chen, Bhavya Kailkhura, Ryan Goldhahn, Yi Zhou

* 9 pages, 12 figures 

  Access Paper or Ask Questions

Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network


Mar 17, 2021
James Diffenderfer, Bhavya Kailkhura


  Access Paper or Ask Questions

Robusta: Robust AutoML for Feature Selection via Reinforcement Learning


Jan 15, 2021
Xiaoyang Wang, Bo Li, Yibo Zhang, Bhavya Kailkhura, Klara Nahrstedt


  Access Paper or Ask Questions

Attribute-Guided Adversarial Training for Robustness to Natural Perturbations


Dec 03, 2020
Tejas Gokhale, Rushil Anirudh, Bhavya Kailkhura, Jayaraman J. Thiagarajan, Chitta Baral, Yezhou Yang

* Accepted to AAAI 2021. Preprint 

  Access Paper or Ask Questions

Leveraging Uncertainty from Deep Learning for Trustworthy Materials Discovery Workflows


Dec 02, 2020
Jize Zhang, Bhavya Kailkhura, T. Yong-Jin Han


  Access Paper or Ask Questions

How Robust are Randomized Smoothing based Defenses to Data Poisoning?


Dec 02, 2020
Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Jihun Hamm


  Access Paper or Ask Questions

FedCluster: Boosting the Convergence of Federated Learning via Cluster-Cycling


Sep 22, 2020
Cheng Chen, Ziyi Chen, Yi Zhou, Bhavya Kailkhura

* 10 pages, 6 figures 

  Access Paper or Ask Questions

Probabilistic Neighbourhood Component Analysis: Sample Efficient Uncertainty Estimation in Deep Learning


Jul 18, 2020
Ankur Mallick, Chaitanya Dwivedi, Bhavya Kailkhura, Gauri Joshi, T. Yong-Jin Han


  Access Paper or Ask Questions

Explainable Deep Learning for Uncovering Actionable Scientific Insights for Materials Discovery and Design


Jul 16, 2020
Shusen Liu, Bhavya Kailkhura, Jize Zhang, Anna M. Hiszpanski, Emily Robertson, Donald Loveland, T. Yong-Jin Han


  Access Paper or Ask Questions

Adversarial Mutual Information for Text Generation


Jun 30, 2020
Boyuan Pan, Yazheng Yang, Kaizhao Liang, Bhavya Kailkhura, Zhongming Jin, Xian-Sheng Hua, Deng Cai, Bo Li

* Published at ICML 2020 

  Access Paper or Ask Questions

Actionable Attribution Maps for Scientific Machine Learning


Jun 30, 2020
Shusen Liu, Bhavya Kailkhura, Jize Zhang, Anna M. Hiszpanski, Emily Robertson, Donald Loveland, T. Yong-Jin Han


  Access Paper or Ask Questions

A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning


Jun 21, 2020
Sijia Liu, Pin-Yu Chen, Bhavya Kailkhura, Gaoyuan Zhang, Alfred Hero, Pramod K. Varshney

* IEEE Signal Processing Magazine 

  Access Paper or Ask Questions

Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning


Mar 16, 2020
Jize Zhang, Bhavya Kailkhura, T. Yong-Jin Han


  Access Paper or Ask Questions

Anomalous Instance Detection in Deep Learning: A Survey


Mar 16, 2020
Saikiran Bulusu, Bhavya Kailkhura, Bo Li, Pramod K. Varshney, Dawn Song


  Access Paper or Ask Questions

Automatic Perturbation Analysis on General Computational Graphs


Feb 28, 2020
Kaidi Xu, Zhouxing Shi, Huan Zhang, Minlie Huang, Kai-Wei Chang, Bhavya Kailkhura, Xue Lin, Cho-Jui Hsieh


  Access Paper or Ask Questions

Towards an Efficient and General Framework of Robust Training for Graph Neural Networks


Feb 25, 2020
Kaidi Xu, Sijia Liu, Pin-Yu Chen, Mengshu Sun, Caiwen Ding, Bhavya Kailkhura, Xue Lin

* Accepted by ICASSP 2020 

  Access Paper or Ask Questions

MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking


Feb 07, 2020
Rushil Anirudh, Jayaraman J. Thiagarajan, Bhavya Kailkhura, Timo Bremer

* Minor revision at the International Journal on Computer Vision's (IJCV) special issue on GANs (2020) 

  Access Paper or Ask Questions

Merlin: Enabling Machine Learning-Ready HPC Ensembles


Dec 05, 2019
J. Luc Peterson, Rushil Anirudh, Kevin Athey, Benjamin Bay, Peer-Timo Bremer, Vic Castillo, Francesco Di Natale, David Fox, Jim A. Gaffney, David Hysom, Sam Ade Jacobs, Bhavya Kailkhura, Joe Koning, Bogdan Kustowski, Steven Langer, Peter Robinson, Jessica Semler, Brian Spears, Jayaraman Thiagarajan, Brian Van Essen, Jae-Seung Yeom

* 10 pages, 5 figures; Submitted to IPDPS 2020 

  Access Paper or Ask Questions

Deep Probabilistic Kernels for Sample-Efficient Learning


Oct 13, 2019
Ankur Mallick, Chaitanya Dwivedi, Bhavya Kailkhura, Gauri Joshi, T. Yong-Jin Han


  Access Paper or Ask Questions

On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method


Jul 26, 2019
Pu Zhao, Sijia Liu, Pin-Yu Chen, Nghia Hoang, Kaidi Xu, Bhavya Kailkhura, Xue Lin

* accepted by ICCV 2019 

  Access Paper or Ask Questions

Generative Counterfactual Introspection for Explainable Deep Learning


Jul 06, 2019
Shusen Liu, Bhavya Kailkhura, Donald Loveland, Yong Han


  Access Paper or Ask Questions

A Look at the Effect of Sample Design on Generalization through the Lens of Spectral Analysis


Jun 08, 2019
Bhavya Kailkhura, Jayaraman J. Thiagarajan, Qunwei Li, Peer-Timo Bremer


  Access Paper or Ask Questions

Reliable and Explainable Machine Learning Methods for Accelerated Material Discovery


Jan 05, 2019
Bhavya Kailkhura, Brian Gallagher, Sookyung Kim, Anna Hiszpanski, T. Yong-Jin Han


  Access Paper or Ask Questions

MR-GAN: Manifold Regularized Generative Adversarial Networks


Nov 22, 2018
Qunwei Li, Bhavya Kailkhura, Rushil Anirudh, Yi Zhou, Yingbin Liang, Pramod Varshney

* arXiv admin note: text overlap with arXiv:1706.04156 by other authors 

  Access Paper or Ask Questions

MimicGAN: Corruption-Mimicking for Blind Image Recovery & Adversarial Defense


Nov 20, 2018
Rushil Anirudh, Jayaraman J. Thiagarajan, Bhavya Kailkhura, Timo Bremer


  Access Paper or Ask Questions

Universal Decision-Based Black-Box Perturbations: Breaking Security-Through-Obscurity Defenses


Nov 13, 2018
Thomas A. Hogan, Bhavya Kailkhura


  Access Paper or Ask Questions