Jonathan Z. Bakdash

Laura R. Marusich, Jonathan Z. Bakdash, Yan Zhou et al.

AI Uncertainty Quantification (UQ) has the potential to improve human decision-making beyond AI predictions alone by providing additional probabilistic information to users. The majority of past research on AI and human decision-making has concentrated on model explainability and interpretability, with little focus on understanding the potential impact of UQ on human decision-making. We evaluated the impact on human decision-making for instance-level UQ, calibrated using a strict scoring rule, in two online behavioral experiments. In the first experiment, our results showed that UQ was beneficial for decision-making performance compared to only AI predictions. In the second experiment, we found UQ had generalizable benefits for decision-making across a variety of representations for probabilistic information. These results indicate that implementing high quality, instance-level UQ for AI may improve decision-making with real systems compared to AI predictions alone.

Laura R. Marusich, Mary Grace Kozuch Dhooghe, Jonathan Z. Bakdash et al.

Large language models (LLMs) have the potential to aid and improve human decision-making in classification tasks, not only by providing fairly accurate predictions, but also in their ability to generate cogent narrative explanations of those predictions. Prior work has demonstrated that people generally find AI narrative explanations to be understandable, trustworthy, and convincing for changing beliefs and opinions; however, less is known about the impact of narrative explanations on objective human decision-making performance. Here we conduct a large-scale human behavioral experiment to evaluate decision-making performance with LLM-generated narrative explanations of varying persuasiveness. We found the degree of persuasiveness, or lack thereof, for LLM-based explanations did not meaningfully impact decision accuracy over a simple AI prediction alone, in agreement with typical results with explainable AI based on feature importance. We found evidence that narratives increased reliance on AI, but both when the AI prediction was correct and incorrect. Exploratory analyses also indicated that the more persuasive narratives may have had a detrimental effect on decision response times and the ability to discriminate between a correct and incorrect AI prediction. Overall, this work indicates that including narrative explanations with AI predictions may involve tradeoffs for decision-making performance, and more work is needed to determine how and when narrative explanations impact human decision-making.

Yasmeen Alufaisan, Laura R. Marusich, Jonathan Z. Bakdash et al.

Explainable AI provides insight into the "why" for model predictions, offering potential for users to better understand and trust a model, and to recognize and correct AI predictions that are incorrect. Prior research on human and explainable AI interactions has focused on measures such as interpretability, trust, and usability of the explanation. Whether explainable AI can improve actual human decision-making and the ability to identify the problems with the underlying model are open questions. Using real datasets, we compare and evaluate objective human decision accuracy without AI (control), with an AI prediction (no explanation), and AI prediction with explanation. We find providing any kind of AI prediction tends to improve user decision accuracy, but no conclusive evidence that explainable AI has a meaningful impact. Moreover, we observed the strongest predictor for human decision accuracy was AI accuracy and that users were somewhat able to detect when the AI was correct versus incorrect, but this was not significantly affected by including an explanation. Our results indicate that, at least in some situations, the "why" information provided in explainable AI may not enhance user decision-making, and further research may be needed to understand how to integrate explainable AI into real systems.

Jonathan Z. Bakdash, Steve Hutchinson, Erin G. Zaroukian et al.

There have been extensive efforts in government, academia, and industry to anticipate, forecast, and mitigate cyber attacks. A common approach is time-series forecasting of cyber attacks based on data from network telescopes, honeypots, and automated intrusion detection/prevention systems. This research has uncovered key insights such as systematicity in cyber attacks. Here, we propose an alternate perspective of this problem by performing forecasting of attacks that are analyst-detected and -verified occurrences of malware. We call these instances of malware cyber event data. Specifically, our dataset was analyst-detected incidents from a large operational Computer Security Service Provider (CSSP) for the U.S. Department of Defense, which rarely relies only on automated systems. Our data set consists of weekly counts of cyber events over approximately seven years. Since all cyber events were validated by analysts, our dataset is unlikely to have false positives which are often endemic in other sources of data. Further, the higher-quality data could be used for a number for resource allocation, estimation of security resources, and the development of effective risk-management strategies. We used a Bayesian State Space Model for forecasting and found that events one week ahead could be predicted. To quantify bursts, we used a Markov model. Our findings of systematicity in analyst-detected cyber attacks are consistent with previous work using other sources. The advanced information provided by a forecast may help with threat awareness by providing a probable value and range for future cyber events one week ahead. Other potential applications for cyber event forecasting include proactive allocation of resources and capabilities for cyber defense (e.g., analyst staffing and sensor configuration) in CSSPs. Enhanced threat awareness may improve cybersecurity.

Alun Preece, Chris Gwilliams, Christos Parizas et al.

Recent developments in sensing technologies, mobile devices and context-aware user interfaces have made it possible to represent information fusion and situational awareness as a conversational process among actors - human and machine agents - at or near the tactical edges of a network. Motivated by use cases in the domain of security, policing and emergency response, this paper presents an approach to information collection, fusion and sense-making based on the use of natural language (NL) and controlled natural language (CNL) to support richer forms of human-machine interaction. The approach uses a conversational protocol to facilitate a flow of collaborative messages from NL to CNL and back again in support of interactions such as: turning eyewitness reports from human observers into actionable information (from both trained and untrained sources); fusing information from humans and physical sensors (with associated quality metadata); and assisting human analysts to make the best use of available sensing assets in an area of interest (governed by management and security policies). CNL is used as a common formal knowledge representation for both machine and human agents to support reasoning, semantic information fusion and generation of rationale for inferences, in ways that remain transparent to human users. Examples are provided of various alternative styles for user feedback, including NL, CNL and graphical feedback. A pilot experiment with human subjects shows that a prototype conversational agent is able to gather usable CNL information from untrained human subjects.