Verification and Repair of Neural Networks
Keywords:PEAI: Safety Robustness & Trustworthiness, ML: Adversarial Learning & Robustness, CSO: Applications, CSO: Satisfiability Modulo Theories, CSO: Constraint Satisfaction
AbstractNeural 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.
How to Cite
Guidotti, D. (2021). Verification and Repair of Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15714-15715. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17854
The Twenty-Sixth AAAI/SIGAI Doctoral Consortium