I am a second-year PhD student at MIT, fortunate to be coadvised by Costis
Daskalakis and Aleksander Madry. I recently graduated from MIT with a concurrent B.S./M.Eng, double majoring (for B.S.) in Computer Science and
Math. I am supported by the Open Philanthropy AI
My master’s thesis was supervised by Costis Daskalakis at MIT CSAIL. I’m also a founding member of labsix.
In past years, I’ve worked in the MIT CBMM, the Database Lab at MIT, and as an intern at Two Sigma Labs, where I worked on Convex Optimization and Online Learning.
Adversarial Robustness as a Prior for Learned Representations
Logan Engstrom*, Andrew Ilyas*, Shibani Santurkar*, Dimitris Tsipras*, Brandon Tran*, Aleksander Madry (2019)
Blog Post, Github
Adversarial Examples are not Bugs, They are Features
Andrew Ilyas*, Shibani Santurkar*, Dimitris Tsipras*, Logan Engstrom*, Brandon Tran, Aleksander Madry (2019)
Blog Post, Datasets
Spotlight presentation, NeurIPS 2019
Are Deep Policy Gradient Algorithms Truly Policy Gradient Algorithms?
Andrew Ilyas*, Logan Engstrom*, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Madry (2018)
Blog Post (1/3), Blog Post (2/3), Blog Post (3/3)
Prior Convictions: Black-box Adversarial Attacks with Bandits and Priors
Andrew Ilyas*, Logan Engstrom*, Aleksander Madry
ICLR 2019. Github
Black-box Adversarial Attacks with Limited Queries and Information
Andrew Ilyas*, Logan Engstrom*, Anish Athalye*, Jessy Lin*
ICML 2018. Partial-Information/GCV Blog Post, Label-Only Attack Blog Post, Github
MicroFilters: Harnessing Twitter for Disaster Managment
Chairman’s award winner, IEEE GHTC 2015.
Evaluating and Understanding the Robustness of Adversarial Logit Pairing
Logan Engstrom*, Andrew Ilyas*, Anish Athalye* (2018)
NeurIPS Security in Machine Learning Workshop 2018
In this section I have included a list of previous hardware/software projects, including hackathon products, and weekend projects.
A visual interface for creating ConvNets built at MHacks 8, written in JS (frontend) and Torch7/Lua: Code on Github
A chrome extension that indexes browser history based on page content, improving history search. Also available on Github
A 3D modeling tutorial, currently on YouTube, made in an earlier Grade – I made a camera using Lightwave 9.
In January of 2015, I built a fully-functioning 8p trivia system for my school club.
In 2012, I led my school robotics team to a Qatar National Championship.
One of the apps that I have made, the Lightning Labyrinth, is now available for download on the App Store.
The first project I worked on under Prof. Madden at MIT &endash; A visualization of dangerous events in cars around the world.
The second and main project I worked on under Prof. Madden at MIT &endash; a possible solution to texting-while-driving.
I taught my sister the fundamentals of electricity and Arduino with this Tic-Tac-Toe Machine.
In this section I have included a near-complete list of previous research topics, and links to the papers, reports, or products created as a result of that research. The projects are sorted chronologically, from 2009 to 2015.