36
Publications
3.8K
Citations
25
H-Index
2014
Active since
Andrew Ilyas is an author at Massachusetts Institute of Technology specializing in engineering, computer science, and machine learning.
Top concepts
EngineeringComputer ScienceMachine LearningData ScienceDeep LearningArtificial IntelligenceAdversarial Machine LearningComputer VisionMachine VisionRobot Learning
Publications per year
2014–2023
36
36
Synthesizing Robust Adversarial Examples
Anish Athalye, Logan Engstrom, Andrew Ilyas et al. · arXiv (Cornell University) · 2017 · 684 citations · Full text
Synthesizing Robust Adversarial Examples
Anish Athalye, Logan Engstrom, Andrew Ilyas et al. · International Conference on Machine Learning · 2018 · 487 citations
Adversarial Examples Are Not Bugs, They Are Features
Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras et al. · arXiv (Cornell University) · 2019 · 395 citations · Full text
Artificial Intelligence, Adversarial Examples, Trustworthy Ai +14
Black-box Adversarial Attacks with Limited Queries and Information
Andrew Ilyas, Logan Engstrom, Anish Athalye et al. · arXiv (Cornell University) · 2018 · 326 citations · Full text
How Does Batch Normalization Help Optimization?
Shibani Santurkar, Dimitris Tsipras, Andrew Ilyas et al. · arXiv (Cornell University) · 2018 · 229 citations · Full text
Artificial Intelligence, Convolutional Neural Network, Engineering +16
Rows per page
1–5 of 36