Providing safety guarantees for autonomous systems is difficult as these...
Transparent and efficient vulnerability and patch disclosure are still a...
Many modern software systems are enabled by deep learning libraries such...
Ensembling certifiably robust neural networks has been shown to be a
pro...
We present DEEPDECS, a new method for the synthesis of
correct-by-constr...
Neural networks are increasingly being deployed in contexts where safety...
This paper presents an evaluation of the code representation model Code2...
We present NNrepair, a constraint-based technique for repairing neural
n...
This paper presents NEUROSPF, a tool for the symbolic analysis of neural...
Inspired by recent successes with parallel optimization techniques for
s...
Local robustness ensures that a model classifies all inputs within an
ϵ-...
Even as deep neural networks have become very effective for tasks in vis...