Verification and Repair of Neural Networks
DOI:
https://doi.org/10.1609/aaai.v35i18.17854Keywords:
PEAI: Safety Robustness & Trustworthiness, ML: Adversarial Learning & Robustness, CSO: Applications, CSO: Satisfiability Modulo Theories, CSO: Constraint SatisfactionAbstract
Neural Networks (NNs) are popular machine learning models which have found successful application in many different domains across computer science. However, it is hard to provide any formal guarantee on the behaviour of neural networks and therefore their reliability is still in doubt, especially concerning their deployment in safety and security-critical applications. Verification emerged as a promising solution to address some of these problems. In the following, I will present some of my recent efforts in verifying NNs.Downloads
Published
2021-05-18
How to Cite
Guidotti, D. (2021). Verification and Repair of Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15714-15715. https://doi.org/10.1609/aaai.v35i18.17854
Issue
Section
The Twenty-Sixth AAAI/SIGAI Doctoral Consortium