12 citations · 12 across the 1 of their papers we have counts for
4 papers
Robustness Certification of Generative Models
Matthew Mirman, Timon Gehr, Martin Vechev
Generative neural networks can be used to specify continuous transformations between images via latent-space interpolation. However, certifying that all images captured by the resu…
Online Robustness Training for Deep Reinforcement Learning
Marc Fischer, Matthew Mirman, Steven Stalder +1
In deep reinforcement learning (RL), adversarial attacks can trick an agent into unwanted states and disrupt training. We propose a system called Robust Student-DQN (RS-DQN), which…
Universal Approximation with Certified Networks
Maximilian Baader, Matthew Mirman, Martin Vechev
Training neural networks to be certifiably robust is critical to ensure their safety against adversarial attacks. However, it is currently very difficult to train a neural network…
A Provable Defense for Deep Residual Networks
Matthew Mirman, Gagandeep Singh, Martin Vechev
We present a training system, which can provably defend significantly larger neural networks than previously possible, including ResNet-34 and DenseNet-100. Our approach is based o…