486 citations · 536 across the 4 of their papers we have counts for
8 papers · 1 filter
Leveraging Sparse Linear Layers for Debuggable Deep Networks
Eric Wong, Shibani Santurkar, Aleksander Mądry
We show how fitting sparse linear models over learned deep feature representations can lead to more debuggable neural networks. These networks remain highly accurate while also bei…
Learning perturbation sets for robust machine learning
Eric Wong, J. Zico Kolter
Although much progress has been made towards robust deep learning, a significant gap in robustness remains between real-world perturbations and more narrowly defined sets typically…
Neural Network Virtual Sensors for Fuel Injection Quantities with Provable Performance Specifications
Eric Wong, Tim Schneider, Joerg Schmitt +2
Recent work has shown that it is possible to learn neural networks with provable guarantees on the output of the model when subject to input perturbations, however these works have…
Overfitting in adversarially robust deep learning
Leslie Rice, Eric Wong, J. Zico Kolter
It is common practice in deep learning to use overparameterized networks and train for as long as possible; there are numerous studies that show, both theoretically and empirically…
Fast is better than free: Revisiting adversarial training
Eric Wong, Leslie Rice, J. Zico Kolter
Adversarial training, a method for learning robust deep networks, is typically assumed to be more expensive than traditional training due to the necessity of constructing adversari…
Adversarial Robustness Against the Union of Multiple Perturbation Models
Pratyush Maini, Eric Wong, J. Zico Kolter
Owing to the susceptibility of deep learning systems to adversarial attacks, there has been a great deal of work in developing (both empirically and certifiably) robust classifiers…