Many papers make claims about specific visualization techniques that are said to enhance or calibrate trust in AI systems. But a design choice that enhances trust in some cases appears to damage it in others. In this paper, we explore this inherent duality through an analogy with "knobs". Turning a knob too far in one direction may result in under-trust, too far in the other, over-trust or, turned up further still, in a confusing distortion. While the designs or so-called "knobs" are not inherently evil, they can be misused or used in an adversarial context and thereby manipulated to mislead users or promote unwarranted levels of trust in AI systems. When a visualization that has no meaningful connection with the underlying model or data is employed to enhance trust, we refer to the result as "trust junk." From a review of 65 papers, we identify nine commonly made claims about trust calibration. We synthesize them into a framework of knobs that can be used for good or "evil," and distill our findings into observed pitfalls for the responsible design of human-AI systems.

Compliance is when a human positively responds to a request or a recommendation given by a system. For example, when prompted, providing your thumbprint for an automated biometric scanner at the airport or starting to watch a new TV show on a streaming service ‘we think you will love’. In trust-related research, compliance is frequently used as a behavioural measure of trust. When evaluating the compliance-trust association in experimental settings, typically, the participants agree, when asked, that they complied because they trusted the system. We developed three scenarios in instantaneous settings where compliance with an instruction delivered by a robot would typically be ascribed to trust. However, rather than asking, ‘Did you trust?’, we asked, ‘Why did you comply?’ In a thematic analysis of responses, we discovered robot design characteristics and sources not related to the design that persuade humans to comply with instructions delivered by a robot.

Every model involves assumptions. While some are standard to all models that simulate intelligent decision-making (e.g., discrete/continuous, static/dynamic), goal recognition is well known also to involve choices about the observed agent: is it aware of being observed? cooperative or adversarial? In this paper, we examine not only these but the many other assumptions made in the context of model-based goal recognition. By exploring their meaning, the relationships between them and the confusions that can arise, we demonstrate their importance, shed light on the way trends emerge in AI, and suggest a novel means for researchers to uncover suitable avenues for future work.

Goal recognition is the problem of determining an agent's intent by observing her behaviour. Contemporary solutions for general task-planning relate the probability of a goal to the cost of reaching it. We adapt this approach to goal recognition in the strict context of path-planning. We show (1) that a simpler formula provides an identical result to current state-of-the-art in less than half the time under all but one set of conditions. Further, we prove (2) that the probability distribution based on this technique is independent of an agent's past behaviour and present a revised formula that achieves goal recognition by reference to the agent's starting point and current location only. Building on this, we demonstrate (3) that a Radius of Maximum Probability (i.e., the distance from a goal within which that goal is guaranteed to be the most probable) can be calculated from relative cost-distances between the candidate goals and a start location, without needing to calculate any actual probabilities. In this extended version of earlier work, we generalise our framework to the continuous domain and discuss our results, including the conditions under which our findings can be generalised back to goal recognition in general task-planning.

"Plan recognition as planning" uses an off-the-shelf planner to perform goal recognition. In this paper, we apply the technique to path-planning. We show that a simpler formula provides an identical result in all but one set of conditions and, further, that identical ranking of goals by probability can be achieved without using any observations other than the agent's start location and where she is "now".

Deceptive path-planning involves finding a path such that the probability of an observer identifying the path's final destination - before it has been reached - is minimised. This paper formalises deception as it applies to path-planning and introduces the notion of a last deceptive point (LDP) which, when measured in terms of 'path completion', can be used to rank paths by their potential to deceive. Building on recent developments in probabilistic goal-recognition, we propose a formula to calculate an optimal LDP and present strategies for the generation of deceptive paths by both simulation ('showing the false') and dissimulation ('hiding the real').