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

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming

Nov 03, 2020
Sumanth Dathathri, Krishnamurthy Dvijotham, Alexey Kurakin, Aditi Raghunathan, Jonathan Uesato, Rudy Bunel, Shreya Shankar, Jacob Steinhardt, Ian Goodfellow, Percy Liang, Pushmeet Kohli


  Access Paper or Ask Questions

Measuring Massive Multitask Language Understanding

Sep 21, 2020
Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, Jacob Steinhardt

* The test and code is available at https://github.com/hendrycks/test 

  Access Paper or Ask Questions

Aligning AI With Shared Human Values

Aug 05, 2020
Dan Hendrycks, Collin Burns, Steven Basart, Andrew Critch, Jerry Li, Dawn Song, Jacob Steinhardt


  Access Paper or Ask Questions

The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization

Jun 29, 2020
Dan Hendrycks, Steven Basart, Norman Mu, Saurav Kadavath, Frank Wang, Evan Dorundo, Rahul Desai, Tyler Zhu, Samyak Parajuli, Mike Guo, Dawn Song, Jacob Steinhardt, Justin Gilmer

* Datasets, code, and models available at https://github.com/hendrycks/imagenet-r 

  Access Paper or Ask Questions

Robust estimation via generalized quasi-gradients

May 28, 2020
Banghua Zhu, Jiantao Jiao, Jacob Steinhardt


  Access Paper or Ask Questions

Identifying Statistical Bias in Dataset Replication

May 19, 2020
Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Jacob Steinhardt, Aleksander Madry


  Access Paper or Ask Questions

Rethinking Bias-Variance Trade-off for Generalization of Neural Networks

Mar 21, 2020
Zitong Yang, Yaodong Yu, Chong You, Jacob Steinhardt, Yi Ma


  Access Paper or Ask Questions

When does the Tukey median work?

Jan 21, 2020
Banghua Zhu, Jiantao Jiao, Jacob Steinhardt


  Access Paper or Ask Questions

A Benchmark for Anomaly Segmentation

Nov 25, 2019
Dan Hendrycks, Steven Basart, Mantas Mazeika, Mohammadreza Mostajabi, Jacob Steinhardt, Dawn Song

* StreetHazards dataset and code are available at https://github.com/hendrycks/anomaly-seg 

  Access Paper or Ask Questions

Generalized Resilience and Robust Statistics

Sep 19, 2019
Banghua Zhu, Jiantao Jiao, Jacob Steinhardt


  Access Paper or Ask Questions

Testing Robustness Against Unforeseen Adversaries

Aug 21, 2019
Daniel Kang, Yi Sun, Dan Hendrycks, Tom Brown, Jacob Steinhardt


  Access Paper or Ask Questions

Natural Adversarial Examples

Jul 18, 2019
Dan Hendrycks, Kevin Zhao, Steven Basart, Jacob Steinhardt, Dawn Song

* Dataset and code available at https://github.com/hendrycks/natural-adv-examples 

  Access Paper or Ask Questions

Transfer of Adversarial Robustness Between Perturbation Types

May 03, 2019
Daniel Kang, Yi Sun, Tom Brown, Dan Hendrycks, Jacob Steinhardt

* 11 pages, 6 figures 

  Access Paper or Ask Questions

Semidefinite relaxations for certifying robustness to adversarial examples

Nov 02, 2018
Aditi Raghunathan, Jacob Steinhardt, Percy Liang

* To appear at NIPS 2018 

  Access Paper or Ask Questions

Stronger Data Poisoning Attacks Break Data Sanitization Defenses

Nov 02, 2018
Pang Wei Koh, Jacob Steinhardt, Percy Liang


  Access Paper or Ask Questions

Does robustness imply tractability? A lower bound for planted clique in the semi-random model

Sep 04, 2018
Jacob Steinhardt

* Improved lower bound to give recovery probability tending to zero. Factored out and highlighted perturbed Bernoulli argument 

  Access Paper or Ask Questions

Troubling Trends in Machine Learning Scholarship

Jul 26, 2018
Zachary C. Lipton, Jacob Steinhardt

* Presented at ICML 2018: The Debates 

  Access Paper or Ask Questions

Sever: A Robust Meta-Algorithm for Stochastic Optimization

Mar 07, 2018
Ilias Diakonikolas, Gautam Kamath, Daniel M. Kane, Jerry Li, Jacob Steinhardt, Alistair Stewart


  Access Paper or Ask Questions

The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation

Feb 20, 2018
Miles Brundage, Shahar Avin, Jack Clark, Helen Toner, Peter Eckersley, Ben Garfinkel, Allan Dafoe, Paul Scharre, Thomas Zeitzoff, Bobby Filar, Hyrum Anderson, Heather Roff, Gregory C. Allen, Jacob Steinhardt, Carrick Flynn, Se√°n √ď h√Čigeartaigh, Simon Beard, Haydn Belfield, Sebastian Farquhar, Clare Lyle, Rebecca Crootof, Owain Evans, Michael Page, Joanna Bryson, Roman Yampolskiy, Dario Amodei


  Access Paper or Ask Questions

Certified Defenses against Adversarial Examples

Jan 29, 2018
Aditi Raghunathan, Jacob Steinhardt, Percy Liang


  Access Paper or Ask Questions

Resilience: A Criterion for Learning in the Presence of Arbitrary Outliers

Nov 27, 2017
Jacob Steinhardt, Moses Charikar, Gregory Valiant

* 32 pages, full version of ITCS2018 paper (minor citation edit from v2) 

  Access Paper or Ask Questions

Certified Defenses for Data Poisoning Attacks

Nov 24, 2017
Jacob Steinhardt, Pang Wei Koh, Percy Liang

* Appeared at NIPS 2017 

  Access Paper or Ask Questions

Better Agnostic Clustering Via Relaxed Tensor Norms

Nov 20, 2017
Pravesh K. Kothari, Jacob Steinhardt


  Access Paper or Ask Questions

Learning from Untrusted Data

Jun 11, 2017
Moses Charikar, Jacob Steinhardt, Gregory Valiant

* Updated based on STOC camera-ready 

  Access Paper or Ask Questions

Concrete Problems in AI Safety

Jul 25, 2016
Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, Dan Mané

* 29 pages 

  Access Paper or Ask Questions

Avoiding Imposters and Delinquents: Adversarial Crowdsourcing and Peer Prediction

Jun 16, 2016
Jacob Steinhardt, Gregory Valiant, Moses Charikar

* 18 pages 

  Access Paper or Ask Questions