In order to train networks for verified adversarial robustness, previous...
Recent work provides promising evidence that Physics-informed neural net...
Safety certification of data-driven control techniques remains a major o...
Recent works have tried to increase the verifiability of adversarially
t...
We improve the scalability of Branch and Bound (BaB) algorithms for form...
We propose a general framework for verifying input-output specifications...
Tight and efficient neural network bounding is of critical importance fo...
Convex optimization problems with staged structure appear in several
con...
Convex relaxations have emerged as a promising approach for verifying
de...
Reliable detection of out-of-distribution (OOD) inputs is increasingly
u...
A fundamental component of neural network verification is the computatio...
The success of Deep Learning and its potential use in many safety-critic...
Models such as Sequence-to-Sequence and Image-to-Sequence are widely use...
Prior work on neural network verification has focused on specifications ...
Recent works have shown that it is possible to train models that are
ver...
Dense conditional random fields (CRFs) with Gaussian pairwise potentials...
Program synthesis is the task of automatically generating a program
cons...
The success of Deep Learning and its potential use in many important saf...
Most recently proposed methods for Neural Program Induction work under t...
The fully connected conditional random field (CRF) with Gaussian pairwis...
Dense conditional random fields (CRF) with Gaussian pairwise potentials ...