AI Ethics and Multiagent Systems

Ethics is inherently a multiagent concern an amalgam of (1) one party's concern for another and (2) a notion of justice. To capture the multiagent conception, this tutorial introduces ethics as a sociotechnical construct. Specifically, we demonstrate how ethics can be modeled and analyzed, and requirements on ethics (value preferences) can be elicited, in a sociotechnical system (STS). An STS comprises of autonomous social entities (principals, i.e., people and organizations), and technical entities (agents, who help principals), and resources (e.g., data, services, sensors, and actuators). 

Tutorials

Recent

Past Tutorials

Selected Publications

(Rishabh Agrawal, Nirav Ajmeri, and Munindar P. Singh) Socially Intelligent Genetic Agents for the Emergence of Explicit Norms. Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI), Stockholm, July 2022, pages 16.

(Jessica Woodgate and Nirav Ajmeri) Macro Ethics for Governing Equitable Sociotechnical Systems. Proceedings of the 21st Conference on Autonomous Agents and MultiAgent Systems, Virtual, May 2022, pages 18241828.

(Enrico Liscio, Michiel van der Meer, Luciano C. Siebert, Catholijn M. Jonker, Niek Mouter, and Pradeep K. Murukannaiah) Axies: Identifying and Evaluating Context-Specific Values. Proceedings of the 20th Conference on Autonomous Agents and MultiAgent Systems, London, May 2021, pages 799808.

(Pradeep K. Murukannaiah and Munindar P. Singh) From Machine Ethics to Internet Ethics: Broadening the Horizon, IEEE Internet Computing, volume 24, number 3, May 2020, pages 51–57. doi: 10.1109/MIC.2020.2989935 

(Nirav Ajmeri, Hui Guo, Pradeep K. Murukannaiah, and Munindar P. Singh) Elessar: Ethics in Norm-Aware Agents. Proceedings of the 19th Conference on Autonomous Agents and MultiAgent Systems (AAMAS). Auckland, May 2020, pages 16–24.

(Pradeep K. Murukannaiah, Nirav Ajmeri, Catholijn M. Jonker, and Munindar P. Singh) New Foundations of Ethical Multiagent Systems. Proceedings of the 19th Conference on Autonomous Agents and MultiAgent Systems (AAMAS) Blue Sky Track. Auckland, May 2020, pages 1706–1710.

(Özgür Kafalı, Nirav Ajmeri, and Munindar P. Singh) Specification of Sociotechnical Systems via Patterns of Regulation and Control. ACM Transactions on Software Engineering and Methodology (TOSEM), volume 29, number 1, pages 7:1–7:50, February 2020 (includes supplement).

(Nirav Ajmeri, Hui Guo, Pradeep K. Murukannaiah, and Munindar P. Singh) Designing Ethical Personal Agents. IEEE Internet Computing, vol 22, number 2, March-April 2018, pages 1622.

(Amit K. Chopra and Munindar P. Singh) Sociotechnical Systems and Ethics in the Large. Proceedings of the 1st AAAI/ACM Conference on AI, Ethics, and Society (AIES), New Orleans, February 2018, pages 48–53.

(Nirav Ajmeri, Hui Guo, Pradeep K. Murukannaiah, and Munindar P. Singh) Robust Norm Emergence by Revealing and Reasoning about Context: Socially Intelligent Agents for Enhancing Privacy. Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI), Stockholm, July 2018, pages 28–34.

(Nirav Ajmeri, Hui Guo, Pradeep K. Murukannaiah, and Munindar P. Singh) Arnor: Modeling Social Intelligence via Norms to Engineer Privacy-Aware Personal Agents. Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems (AAMAS). São Paulo, May 2017, pages 230–238. 

(Pradeep K. Murukannaiah, Nirav Ajmeri, Munindar P. Singh) Engineering Privacy in Social Applications. IEEE Internet Computing, volume 20, number 2, pages 7276, March 2016. 

(Pradeep K. Murukannaiah and Munindar P. Singh) Xipho: Extending Tropos to Engineer Context-Aware Personal Agents. Proceedings of the 13th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS). May 2014, pages 309–316. 

Contributors

Nirav Ajmeri (University of Bristol)

Nirav Ajmeri is a Lecturer in Artificial Intelligence at the University of Bristol in the United Kingdom.  His research interests are in intelligent agents and multiagent systems with an emphasis on ethics, privacy, and security. Nirav's research seeks to facilitate engineering a society of socially intelligent agents that act ethically and yield a satisfactory experience to their users.  His research has appeared in top AI and computing venues including AAMAS, AAAI, IJCAI, IEEE Computer, IEEE Intelligent Systems, IEEE Internet Computing, and ACM TOSEM. Contact Nirav at nirav.ajmeri@bristol.ac.uk.


Pradeep Murukannaiah (Delft University of Technology)

Pradeep Murukanniah is an Assistant Professor in the Interactive Intelligence group at the Delft University of Technology in the Netherlands.  Prior to TU Delft, Pradeep was an Assistant Professor in the Software Engineering department at Rochester Institute of Technology. Engineering socially intelligent agents is the overarching theme of Pradeep's research. His works facilitate sociotechnical systems that support rich interactions between humans and computational agents, enabling a variety of individual and societal applications. Pradeep's research has appeared in prestigious AI conferences (including AAMAS, IJCAI, ACL, and RecSys) and computing journals (including ACM TOSEM, and ACM TOCHI). Pradeep delivered an invited talk on Privacy Analytics at the 2017 International Conference on Privacy, Security, and Trust. Contact Pradeep at p.k.murukannaiah@tudelft.nl.

Munindar P. Singh (North Carolina State University)

Munindar P. Singh is a Professor in Computer Science and a co-director of the Science of Security  Lablet  at North Carolina State University.  His research interests include multiagent systems and software engineering with a special emphasis on the engineering of systems consisting of autonomous parties.  He coauthored the text Service-Oriented Computing in 2005. Munindar is an IEEE Fellow, a AAAI Fellow, a AAAS Fellow, an ACM Fellow, and a former Editor-in-Chief of IEEE Internet Computing and ACM Transactions on Internet Technology.  His current editorial service includes IEEE Internet Computing, IEEE Transactions on Services Computing, Autonomous Agents and Multiagent Systems, and the ACM Transactions on Intelligent Systems and Technology.  His prior editorial service includes Journal of Artificial Intelligence Research and Journal of Web Semantics. Munindar was general cochair of AAMAS 2005 and program cochair of CoopIS 1997, ICWS 2008, and several other events.  He was a member of the founding IFAAMAS Board of Directors. Contact Munindar at singh@ncsu.edu.