Safety Analysis of Deep Neural Networks
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Doctoral Consortium. Pages 4887-4888.
https://doi.org/10.24963/ijcai.2021/675
Keywords
- AI Ethics, Trust, Fairness: Trustable Learning
- Machine Learning: Adversarial Machine Learning
- Machine Learning: Deep Learning
- Multidisciplinary Topics and Applications: Validation and Verification
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.
@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 = {Prof. 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},
}
TY - CPAPER TI - Safety Analysis of Deep Neural Networks AU - Guidotti, Dario T2 - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21 PB - International Joint Conferences on Artificial Intelligence Organization PY - 2021 SP - 4887 EP - 4888 DO - 10.24963/ijcai.2021/675 UR - https://doi.org/10.24963/ijcai.2021/675 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
