Logan EngstromEmail: email@example.com
Google Scholar: here
I'm a fourth year undergraduate at MIT studying Computer Science. I'm most interested in machine learning, optimization, and statistics. I currently work with Aleksander Mądry at MIT. I am generously supported through a Siebel Scholarship. I previously interned at Two Sigma (summer 2018), Google Brain (summer 2017) and Apple (summer 2016).
At MIT I played for the ESP intramural football (before a season ending shoulder dislocation) and dodgeball teams. I used to organize HackMIT and help out in USAGE, the undergraduate advisory board for MIT EECS.
Anish Athalye*, Logan Engstrom*, Andrew Ilyas*, and Kevin Kwok. Synthesizing Robust Adversarial Examples. ICML 2018, 2017.
Andrew Ilyas*, Logan Engstrom*, Anish Athalye*, and Jessy Lin*. Black-box Adversarial Attacks with Limited Queries and Information. ICML 2018, 2017.
Logan Engstrom*, Brandon Tran*, Dimitris Tsipras*, Ludwig Schmidt, and Aleksander Mądry. A Rotation and a Translation Suffice: Fooling CNNs with Simple Transformations. NIPS Machine Learning and Computer Security Workshop, 2018.
Daniel Kang, Richard Sherwood, Amira Barkal, Tatsunori Hashimoto, Logan Engstrom, and David Gifford. DNase-capture Reveals Differential Transcription Factor Binding modalities. PloS one, 2017.
Andrew Ilyas*, Logan Engstrom*, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, and Aleksander Mądry.
Are Deep Policy Gradient Algorithms
Dimitris Tsipras*, Shibani Santurkar*, Logan Engstrom*, Alexander Turner, and Aleksander Mądry. Robustness May Be at Odds with Accuracy. 2018.
Andrew Ilyas*, Logan Engstrom*, Ludwig Schmidt, and Aleksander Mądry. Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors. 2018.
Logan Engstrom*, Andrew Ilyas*, and Anish Athalye*. Evaluating and Understanding the Robustness of Adversarial Logit Pairing. 2018.