Neural networks are notoriously vulnerable to adversarial attacks – smal...
Over-approximating the reachable sets of dynamical systems is a fundamen...
We propose a novel Branch-and-Bound method for reachability analysis of
...
The rotation search problem aims to find a 3D rotation that best aligns ...
Analyzing the worst-case performance of deep neural networks against inp...
Mirror descent (MD) is a powerful first-order optimization technique tha...
We exploit recent results in quantifying the robustness of neural networ...
Abstracting neural networks with constraints they impose on their inputs...
When designing controllers for safety-critical systems, practitioners of...
Complementarity problems, a class of mathematical optimization problems ...
The fragility of deep neural networks to adversarially-chosen inputs has...
There has been an increasing interest in using neural networks in closed...
Quantifying the robustness of neural networks or verifying their safety
...
Tight estimation of the Lipschitz constant for deep neural networks (DNN...
Analyzing the robustness of neural networks against norm-bounded
uncerta...