8 citations · 27 across the 23 of their papers we have counts for
4 papers · 1 filter
The Fundamental Limits of Interval Arithmetic for Neural Networks
Matthew Mirman, Maximilian Baader, Martin Vechev
Interval analysis (or interval bound propagation, IBP) is a popular technique for verifying and training provably robust deep neural networks, a fundamental challenge in the area o…
Latent Space Smoothing for Individually Fair Representations
Momchil Peychev, Anian Ruoss, Mislav Balunović +2
Fair representation learning transforms user data into a representation that ensures fairness and utility regardless of the downstream application. However, learning individually f…
Scalable Certified Segmentation via Randomized Smoothing
Marc Fischer, Maximilian Baader, Martin Vechev
We present a new certification method for image and point cloud segmentation based on randomized smoothing. The method leverages a novel scalable algorithm for prediction and certi…
On the Paradox of Certified Training
Nikola Jovanović, Mislav Balunović, Maximilian Baader +1
Certified defenses based on convex relaxations are an established technique for training provably robust models. The key component is the choice of relaxation, varying from simple…