---
title: "Safety Analysis of Deep Neural Networks"
authors:
  - "Dario Guidotti"
doi: "10.24963/ijcai.2021/675"
url: "https://ijcai.org/proceedings/2021/675"
pdf: "https://ijcai.org/proceedings/2021/0675.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "4887-4888"
track: "Doctoral Consortium"
keywords:
  - "AI Ethics, Trust, Fairness: Trustable Learning"
  - "Machine Learning: Adversarial Machine Learning"
  - "Machine Learning: Deep Learning"
  - "Multidisciplinary Topics and Applications: Validation and Verification"
---

# Safety Analysis of Deep Neural Networks

Dario Guidotti

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 4887-4888. DOI: [10.24963/ijcai.2021/675](https://doi.org/10.24963/ijcai.2021/675)

## 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.