The Second IEEE International Workshop on Workshop on Assured Autonomy, AI and Machine Learning (WAAM 2023)

November 2, 2023. Atlanta, GA, USA

Part of The Fifth IEEE International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications

http://www.sis.pitt.edu/lersais/conference/tps/2023/

November 1-3, 2023. Atlanta, GA, USA

Description

Artificial intelligence (AI) and Machine Learning (ML) systems are increasingly seen in many domains such as self-driving land vehicles, autonomous aircraft, and medical systems. AI systems should equal or surpass human performance, but given the consequences of failure in these systems, how do we determine that the data gathered to train an AI system is suitably representative of the real world? How do we assure the public that these systems work as intended and will not cause harm? These questions have given rise to a new term: “assured autonomy.” In this workshop, issues in assured autonomy such as explain ability, bias, verification, validation, privacy, trust and more for AI and ML systems will be explored. Research, experiences and best practices will be presented to illustrate the challenges and possible approaches to assured autonomy. Finally, the road ahead will be explored.

This workshop will bring together researchers from government, industry and academia to discuss these challenging issues. The workshop will be in the form of panel discussions and invited presentations. While the panelist and presenters are invited only, any conference attendee is welcome to attend the workshop.

Topics to be discussed may include

· Verification and/or validation of AI/ML systems

· Specification and requirements engineering for assured autonomy

· Explainable AI: evaluation and testing

· Bias: sources, identification, impact, and reduction/elimination

· Assured autonomy for

o Transportation, healthcare, financial and all other critical infrastructure systems

o Space applications

o Consumer goods and non-critical applications

o other application domains

· Trust and Artificial trust

· Security, safety and privacy issues for AI/ML systems

· Policies, standards, frameworks, legislative efforts for assured autonomy

· Related topics

A summary of the findings of the Workshop will appear in IEEE Computer magazine and IEEE Reliability magazine.

Workshop Organizers

Phil Laplante, NIST phillip.laplante@nist.gov

Rick Kuhn, NIST rkuhn@nist.gov