Shibani shibani AT stanford DOT edu

                     

Shibani Santurkar


I am a postdoc in the Stanford Computer Science Department, working with Tatsu Hashimoto, Percy Liang, and Tengyu Ma. I am interested in developing machine learning tools that can perform reliably in the real world, and characterizing the consequences if they fail to do so. My postdoctoral research is supported by Open Philanthropy.

I got my PhD from MIT, where I was fortunate to be advised by Aleksander Madry and Nir Shavit. Before that, I graduated from IIT Bombay with a Bachelors and Masters in Electrical Engineering.

Selected Papers

Leveraging Sparse Linear Layers for Debuggable Deep Networks
Eric Wong*, Shibani Santurkar*, Aleksander Madry
ICML 2021 (Long Presentation)
[Blog posts: part 1 and part 2]


BREEDS: Benchmarks for Subpopulation Shift
Shibani Santurkar*, Dimitris Tsipras*, Aleksander Madry
ICLR 2021
[Blog post], [Code and Data]


From ImageNet to Image Classification: Contextualizing Progress on Benchmarks
Dimitris Tsipras*, Shibani Santurkar*, Logan Engstrom, Andrew Ilyas, Aleksander Madry
ICML 2020
[Blog post]


Identifying Statistical Bias in Dataset Replication
Logan Engstrom*, Andrew Ilyas*, Shibani Santurkar, Dimitris Tsipras, Jacob Steinhardt, Aleksander Madry
ICML 2020
[Blog post]


Implementation Matters in Deep RL: A Case Study on PPO and TRPO
Logan Engstrom*, Andrew Ilyas*, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Madry
ICLR 2020 (Oral Presentation)
[Blog posts: part 1 and part 2]


A Closer Look at Deep Policy Gradients
Andrew Ilyas*, Logan Engstrom*, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Madry
ICLR 2020 (Oral Presentation)
[Blog post]


Image Synthesis with a Single (Robust) Classifier
Shibani Santurkar*, Dimitris Tsipras*, Brandon Tran*, Andrew Ilyas*, Logan Engstrom*, Aleksander Madry
NeurIPS 2019
[Blog post], [Code], [Demo]


Learning Perceptually-Aligned Representations via Adversarial Robustness
Logan Engstrom*, Andrew Ilyas*, Shibani Santurkar*, Dimitris Tsipras*, Brandon Tran*, Aleksander Madry
[Blog post], [Code]


Adversarial Examples Are Not Bugs, They Are Features
Andrew Ilyas*, Shibani Santurkar*, Dimitris Tsipras*, Logan Engstrom*, Brandon Tran, Aleksander Madry
NeurIPS 2019 (Spotlight Presentation)
[Blog post], [Datasets]


Robustness May Be at Odds with Accuracy
Dimitris Tsipras*, Shibani Santurkar*, Logan Engstrom*, Alexander Turner, Aleksander Madry
ICLR 2019


How Does Batch Normalization Help Optimization?
Shibani Santurkar*, Dimitris Tsipras*, Andrew Ilyas*, Aleksander Madry
NeurIPS 2018 (Oral Presentation)
[Blog post] , [Short video]


Adversarially Robust Generalization Requires More Data
Ludwig Schmidt, Shibani Santurkar, Dimitris Tsipras, Kunal Talwar, Aleksander Madry
NeurIPS 2018 (Spotlight Presentation)


A Classification-Based Study of Covariate Shift in GAN Distributions
Shibani Santurkar, Ludwig Schmidt, Aleksander Madry
ICML 2018


* Equal Contribution