papers
Publications (7)
cs.CV2018
Black-box Adversarial Attacks with Limited Queries and Information
Andrew Ilyas, Logan Engstrom, Anish Athalye +1
cs.CV2018
Query-Efficient Black-box Adversarial Examples (superceded)
Andrew Ilyas, Logan Engstrom, Anish Athalye +1
stat.ML2019
Adversarial Examples Are Not Bugs, They Are Features
Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras +3
The paper shows that adversarial examples stem from non‑robust features—predictive patterns in data that are fragile and unintelligible to humans—and formalizes their prevalence ac…
#adversarial examples#non-robust features#robustness#theoretical analysis
stat.ML2019
Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors
Andrew Ilyas, Logan Engstrom, Aleksander Madry
stat.ML2018
Evaluating and Understanding the Robustness of Adversarial Logit Pairing
Logan Engstrom, Andrew Ilyas, Anish Athalye
cs.CV2018
Synthesizing Robust Adversarial Examples
Anish Athalye, Logan Engstrom, Andrew Ilyas +1
cs.CV2019
Image Synthesis with a Single (Robust) Classifier
Shibani Santurkar, Dimitris Tsipras, Brandon Tran +3
The paper demonstrates that a single off‑the‑shelf classifier, when trained to be adversarially robust, can be used for various image synthesis tasks by directly manipulating salie…
#image synthesis#adversarial robustness#robust classifiers#feature manipulation