Model-Based Explanation For Human-in-the-Loop Security - July 2019

PI(s), Co-PI(s), Researchers: David Garlan, Bradley Schmerl (CMU)

HARD PROBLEM(S) ADDRESSED
Human Behavior
Metrics
Resilient Architectures

PUBLICATIONS

Ellin Zhao and Roykrong Sukkerd. Interactive Explanation for Planning-Based Systems. In Proceedings of the 10th ACM/IEEE International Conference on Cyberphysical Systems, Work-in-Progress track, Montreal, Canada, 16-18 April 2019.

PUBLIC ACCOMPLISHMENT HIGHLIGHTS
As self-security becomes more automated, it becomes harder for humans who interact with the autonomous system to understand the behavior of the systems. Particularly while optimizing for multiple quality objectives and acting under uncertainty, it can be difficult for humans to understand the system behavior generated by an automated planner. We developed an approach with tool support that aims at clarifying system behavior through interactive explanation by allowing end-users to ask Why and Why-Not questions about specific behaviors of the system, and providing answers in the form of contrastive explanation. In this quarter we designed and piloted a human study to understand the effectiveness of explanations to human operators.

COMMUNITY ENGAGEMENTS (If applicable)

EDUCATIONAL ADVANCES (If applicable)