The IJCAI-ECAI-22 Workshop on Artificial Intelligence Safety (AISafety2022)

Introduction

Safety in Artificial Intelligence (AI) is increasingly becoming a substantial part of AI research, deeply intertwined with the ethical, legal and societal issues associated with AI systems. Even if AI safety is considered a design principle, there are varying levels of safety, diverse sets of ethical standards and values, and varying degrees of liability, for which we need to deal with trade-offs or alternative solutions. These choices can only be analyzed holistically if we integrate technological and ethical perspectives into the engineering problem, and consider both the theoretical and practical challenges for AI safety. This view must cover a wide range of AI paradigms, considering systems that are specific for a particular application, and also those that are more general, which may lead to unanticipated risks. We must bridge the short-term with the long-term perspectives, idealistic goals with pragmatic solutions, operational with policy issues, and industry with academia, in order to build, evaluate, deploy, operate and maintain AI-based systems that are truly safe.

The IJCAI-ECAI-22 Workshop on Artificial Intelligence Safety (AISafety 2022) seeks to explore new ideas in AI safety with a particular focus on addressing the following questions:

Program

The Program Committee (PC) received 26 submissions. Each paper was peer-reviewed by at least two PC members, by following a single-blind reviewing process. The committee decided to accept 13 full papers and 6 short presentations, resulting in a full-paper acceptance rate of 50% and an overall acceptance rate of 73%.

The AISafety 2022 program was organized in six thematic sessions, one (invited) special session, two keynote and four (invited) talks. The special session was given flexibility to structure its program and format.

The thematic sessions followed a highly interactive format. They were structured into short pitches and a group debate panel slot to discuss both individual paper contributions and shared topic issues. Three specific roles were part of this format: session chairs, presenters and session discussants.

• Session Chairs introduced sessions and participants.

The Chair moderated sessions and plenary discussions, monitored time, and moderated questions and discussions from the audience. • Presenters gave a 10-minute paper talk and participated in the debate slot. The short presentations are given 5 minutes for each paper. • Session Discussants gave a critical review of the session papers, and participated in the plenary debate.

Presentations and papers were grouped by topic as follows:

Session 1: AI Ethics: Fairness, Bias, and Accountability

Machine learning for safety-critical AI •Revisiting the Evaluation of Deep Neural Networks for Pedestrian Detection, Patrick Feifel, Benedikt Franke, Arne Raulf, Friedhelm Schwenker, Frank Bonarens and Frank Köster. • Improvement of Rejection for AI Safety through Loss-Based Monitoring, Daniel Scholz, Florian Hauer, Klaus Knobloch and Christian Mayr.• Let it RAIN for Social Good, Mattias Brännström,Andreas Theodorou and Virginia Dignum.• Accountability and Responsibility of ArtificialIntelligence Decision-making Models in Indian PolicyLandscape, Palak Malhotra and Amita Misra.• Assessing Demographic Bias Transfer from Dataset toModel: A Case Study in Facial Expression Recognition,Iris Dominguez-Catena, Daniel Paternain and MikelGalar.Session 2: Short Presentations -Safety Assessment ofAI-enabled systems• A Hierarchical HAZOP-Like Safety Analysis forLearning-Enabled Systems,Yi Qi, Philippa RyanConmy, Wei Huang, Xingyu Zhao and Xiaowei Huang.• Increasingly Autonomous CPS: Taming EmergingBehaviors from an Architectural Perspective, JeromeHugues and Daniela Cancila.• CAISAR: A platform for Characterizing ArtificialIntelligenceSafetyandRobustness,JulienGirard-Satabin, Michele Alberti, François Bobot,Zakaria Chihani and Augustin Lemesle.Session 3: Special

Session : TAILOR -Towards Trustworthy AI •Foundations of Trustworthy AI*, Francesca Pratesi. • Panel on Trustworthy AI*, Fosca Giannotti, Pilipp Slusallek, Giuseppe De Giacomo, Hector Geffner, Holger Hoos.*Presentations without papers.

Acknowledgements

We thank all researchers who submitted papers to AISafety 2022 and congratulate the authors whose papers were selected for inclusion into the workshop program and proceedings.

We especially thank our distinguished PC members for reviewing the submissions and providing useful feedback to the authors:

We thank Gary Marcus, Thomas A. Henzinger, Elizabeth Adams, Luis Aranda, Simos Gerasimou, and Zakaria Chihani for their inspiring talks.

Finally we thank the IJCAI-ECAI-22 organization for providing an excellent framework for AISafety 2022.