Vol-3381
urn:nbn:de:0074-3381-7




SafeAI 2023
Artificial Intelligence Safety 2023


Proceedings of the Workshop on Artificial Intelligence Safety 2023 (SafeAI 2023)
co-located with the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023)

Washington DC, USA, February 13-14, 2023.


Edited by

Gabriel Pedroza *
Xiaowei Huang **
Xin Cynthia Chen ***
Andreas Theodorou ****
José Hernández-Orallo *****
Mauricio Castillo-Effen ******
Richard Mallah *******
John McDermid ********

* Commissariat à l'Energie Atomique, Université Paris-Saclay, France
** University of Liverpool, United Kingdom
*** University of Hong Kong, China
**** Umeå University, Sweden
***** Universitat Politècnica de València, Spain
****** Lockheed Martin, USA
******* Future of Life Institute, USA
******** University of York, United Kingdom




Table of Contents


Session 1: AI/ML Learning, Explainability, Accuracy and Policy Alignment

Session 2: Short Presentations - Safety Assessment of AI-enabled systems

Session 3: AI/ML for Safety Critical Applications: Assurance Cases and Datasets

Session 4 - Short Presentations: ML/DL Robustness: GAM and Attack Detection

Session 5 - AI Safety Assessment: Failure-Cause Analysis, Assurance, Verification

Session 6: AI Robustness: Adversarial and Attacks Learning

Session 7: AI Robustness: Deep Reinforcement Learning

Session 8 - Short Presentations: OoD Detection and Uncertainty for ML/DL Safety

Session 9 - Short Presentations: Methods and Techniques for AI/ML Safety Assessment


2023-03-27: submitted by Xin Cynthia Chen, metadata incl. bibliographic data published under Creative Commons CC0
2023-04-28: published on CEUR Workshop Proceedings (CEUR-WS.org, ISSN 1613-0073) |valid HTML5|