The primary focus of our lab is the science of deep learning. We aim to combine theoretical and empirical insights to build a principled and thorough understanding of key deep learning techniques as well as the challenges we face in this context. The list of topics we are currently exploring includes machine learning security (with an emphasis on adversarial robustness), and the power and limitations of unsupervised deep learning (with a focus on generative adversarial networks).
- We are looking for motivated MIT undergraduate students who would help us build up our infrastructure for deep learning experimentation. Ping us if you are interested!
- Check out our adversarial robustness challenges for MNIST and CIFAR10. Can you break our networks? (We couldn’t.)
Faculty: Aleksander Mądry
Graduate Students: Aleksandar Makelov, Shibani Santurkar, Brandon Tran, Dimitris Tsipras, Kai Xiao
Undergraduate Students: Logan Engstrom, Nur Muhammad Shafiullah, Alexander Turner
Affiliated Researchers: Jerry Li, Ludwig Schmidt
Adversarially Robust Generalization Requires More Data,
Ludwig Schmidt, Shibani Santurkar, Dimitris Tsipras, Kunal Talwar, Aleksander Mądry.
A Classification-Based Perspective on GAN Distributions,
Shibani Santurkar, Ludwig Schmidt, Aleksander Mądry.
ICML 2018.Spotlight presentation at the Deep Learning: Bridging Theory and Practice workshop at NIPS 2017.
Towards Understanding the Dynamics of Generative Adversarial Networks,
Jerry Li, Aleksander Mądry, John Peebles, Ludwig Schmidt (alphabetic order).
ICML 2018.Poster presentation at the Principled Approaches to Deep Learning workshop at ICML 2017.
A Rotation and a Translation Suffice: Fooling CNNs with Simple Transformations,
Logan Engstrom, Brandon Tran, Dimitris Tsipras, Ludwig Schmidt, Aleksander Mądry.
Poster presentation at the Machine Learning and Computer Security workshop at NIPS 2017.
Towards Deep Learning Models Resistant to Adversarial Attacks,
Aleksander Mądry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu (alphabetic order).
ICLR 2018.Oral presentation at the Principled Approaches to Deep Learning workshop at ICML 2017.