SafeAI 2022
Artificial Intelligence Safety 2022

Proceedings of the Workshop on Artificial Intelligence Safety 2022 (SafeAI 2022)
co-located with the Thirty-Sixth AAAI Conference on Artificial Intelligence

Virtual, February, 2022.

Edited by

Gabriel Pedroza *
José Hernández-Orallo **
Xin Cynthia Chen ***
Xiaowei Huang ****
Huáscar Espinoza *****
Mauricio Castillo-Effen ******
John McDermid *******
Richard Mallah ********
Seán Ó hÉigeartaigh *********

* Commissariat à l´Energie Atomique, France
** Universitat Politècnica de València, Spain
*** University of Hong Kong, China
**** University of Liverpool, United Kingdom
***** ECSEL JU, Belgium
****** Lockheed Martin, USA
******* University of York, United Kingdom
******** Future of Life Institute, USA
********* University of Cambridge, United Kingdom

Table of Contents

Session 1: Bias, Fairness and Value Alignment

Session 2: Interpretability and Accountability

Session 3: Robustness and Uncertainty

Session 4: Safe Reinforcement Learning

Session 5: AI Testing and Assessment

Poster Papers

Special Sessions

2022-02-01: submitted by Xin Cynthia Chen, metadata incl. bibliographic data published under Creative Commons CC0
2022-02-15: published on CEUR Workshop Proceedings (CEUR-WS.org, ISSN 1613-0073) |valid HTML5|