IJCAI 2021poster10 citations

Safety Analysis of Deep Neural Networks

Dario Guidotti

Abstract

Deep Neural Networks (DNNs) are popular machine learning models which have found successful application in many different domains across computer science. Nevertheless, providing formal guarantees on the behaviour of neural networks is hard and therefore their reliability in safety-critical domains is still a concern. Verification and repair emerged as promising solutions to address this issue. In the following, I will present some of my recent efforts in this area.

AI Ethics, Trust, Fairness: Trustable LearningMultidisciplinary Topics and Applications: Validation and VerificationMachine Learning: Deep LearningMachine Learning: Adversarial Machine Learning
BibTeX
@inproceedings{ijcai2021p675,
  title     = {Safety Analysis of Deep Neural Networks},
  author    = {Guidotti, Dario},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Zhi-Hua Zhou},
  pages     = {4887--4888},
  year      = {2021},
  month     = {8},
  note      = {Doctoral Consortium},
  doi       = {10.24963/ijcai.2021/675},
  url       = {https://doi.org/10.24963/ijcai.2021/675},
}
Safety Analysis of Deep Neural Networks · IJCAI 2021