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 Logan Engstrom

Unadversarial Examples: Designing Objects for Robust Vision


Dec 22, 2020
Hadi Salman, Andrew Ilyas, Logan Engstrom, Sai Vemprala, Aleksander Madry, Ashish Kapoor


  Access Paper or Ask Questions

Do Adversarially Robust ImageNet Models Transfer Better?


Jul 16, 2020
Hadi Salman, Andrew Ilyas, Logan Engstrom, Ashish Kapoor, Aleksander Madry


  Access Paper or Ask Questions

Noise or Signal: The Role of Image Backgrounds in Object Recognition


Jun 17, 2020
Kai Xiao, Logan Engstrom, Andrew Ilyas, Aleksander Madry


  Access Paper or Ask Questions

Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO


May 25, 2020
Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Madry

* ICLR 2020 version. arXiv admin note: text overlap with arXiv:1811.02553 

  Access Paper or Ask Questions

From ImageNet to Image Classification: Contextualizing Progress on Benchmarks


May 22, 2020
Dimitris Tsipras, Shibani Santurkar, Logan Engstrom, Andrew Ilyas, Aleksander Madry


  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

Computer Vision with a Single (Robust) Classifier


Jun 06, 2019
Shibani Santurkar, Dimitris Tsipras, Brandon Tran, Andrew Ilyas, Logan Engstrom, Aleksander Madry


  Access Paper or Ask Questions

Learning Perceptually-Aligned Representations via Adversarial Robustness


Jun 03, 2019
Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Brandon Tran, Aleksander Madry


  Access Paper or Ask Questions

Adversarial Examples Are Not Bugs, They Are Features


May 07, 2019
Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Logan Engstrom, Brandon Tran, Aleksander Madry


  Access Paper or Ask Questions

Are Deep Policy Gradient Algorithms Truly Policy Gradient Algorithms?


Dec 02, 2018
Andrew Ilyas, Logan Engstrom, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Madry


  Access Paper or Ask Questions

Robustness May Be at Odds with Accuracy


Oct 11, 2018
Dimitris Tsipras, Shibani Santurkar, Logan Engstrom, Alexander Turner, Aleksander Madry


  Access Paper or Ask Questions

Evaluating and Understanding the Robustness of Adversarial Logit Pairing


Jul 26, 2018
Logan Engstrom, Andrew Ilyas, Anish Athalye

* Source code at https://github.com/labsix/adversarial-logit-pairing-analysis 

  Access Paper or Ask Questions

Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors


Jul 20, 2018
Andrew Ilyas, Logan Engstrom, Aleksander Madry


  Access Paper or Ask Questions

Black-box Adversarial Attacks with Limited Queries and Information


Jul 11, 2018
Andrew Ilyas, Logan Engstrom, Anish Athalye, Jessy Lin

* ICML 2018. This supercedes the previous paper "Query-efficient Black-box adversarial examples." 

  Access Paper or Ask Questions

Synthesizing Robust Adversarial Examples


Jun 07, 2018
Anish Athalye, Logan Engstrom, Andrew Ilyas, Kevin Kwok

* ICML 2018 

  Access Paper or Ask Questions

Query-Efficient Black-box Adversarial Examples (superceded)


Apr 06, 2018
Andrew Ilyas, Logan Engstrom, Anish Athalye, Jessy Lin

* Superceded by "Black-Box Adversarial Attacks with Limited Queries and Information." 

  Access Paper or Ask Questions

A Rotation and a Translation Suffice: Fooling CNNs with Simple Transformations


Feb 13, 2018
Logan Engstrom, Brandon Tran, Dimitris Tsipras, Ludwig Schmidt, Aleksander Madry

* Preliminary version appeared in the NIPS 2017 Workshop on Machine Learning and Computer Security 

  Access Paper or Ask Questions