A psycholinguistic analysis of eye-movement patterns while troubleshooting Python source code.
Abstract not provided.
Engineering topics
Publications and source records attributed to Stites, Mallory.
Abstract not provided.
This research explores novel methods for extracting relevant information from EEG data to characterize individual differences in cognitive processing. Our approach combines expertise in machine learning, statistics, and cognitive science, advancing the state-of-the art in all three domains. Specifically, by using cognitive science expertise to interpret results and inform algorithm development, we have developed a generalizable and interpretable machine learning method that can accurately predict individual differences in cognition. The output of the machine learning method revealed surprising features of the EEG data that, when interpreted by the cognitive science experts, provided novel insights to the underlying cognitive task. Additionally, the outputs of the statistical methods show promise as a principled approach to quickly find regions within the EEG data where individual differences lie, thereby supporting cognitive science analysis and informing machine learning models. This work lays methodological ground work for applying the large body of cognitive science literature on individual differences to high consequence mission applications.
With machine learning (ML) technologies rapidly expanding to new applications and domains, users are collaborating with artificial intelligence-assisted diagnostic tools to a larger and larger extent. But what impact does ML aid have on cognitive performance, especially when the ML output is not always accurate? Here, we examined the cognitive effects of the presence of simulated ML assistance—including both accurate and inaccurate output—on two tasks (a domain-specific nuclear safeguards task and domain-general visual search task). Patterns of performance varied across the two tasks for both the presence of ML aid as well as the category of ML feedback (e.g., false alarm). These results indicate that differences such as domain could influence users’ performance with ML aid, and suggest the need to test the effects of ML output (and associated errors) in the specific context of use, especially when the stimuli of interest are vague or ill-defined
When new technology, such as artificial intelligence (AI), is introduced into an existing workflow it may impact risk by mitigating some vulnerabilities and threats in the workflow while introducing others. We present a versatile methodology for assessing the vulnerabilities and threats that impact overall risk in a workflow to inform technology integration. Our method involves both qualitative and quantitative assessment of risk and includes a formula for generating a risk score to guide technology integration. We describe our methodology and demonstrate its application to a specific workflow (the Derivative Classification review process). This work was funded by the Department of Energy (DOE) Automated Classification Tools for the Identification of Classified Information (ACTICI) program.
Abstract not provided.
This report details the results of a three-fold investigation of sensitivity analysis (SA) for machine learning (ML) explainability (MLE): (1) the mathematical assessment of the fidelity of an explanation with respect to a learned ML model, (2) quantifying the trustworthiness of a prediction, and (3) the impact of MLE on the efficiency of end-users through multiple users studies. We focused on the cybersecurity domain as the data is inherently non-intuitive. As ML is being using in an increasing number of domains, including domains where being wrong can elicit high consequences, MLE has been proposed as a means of generating trust in a learned ML models by end users. However, little analysis has been performed to determine if the explanations accurately represent the target model and they themselves should be trusted beyond subjective inspection. Current state-of-the-art MLE techniques only provide a list of important features based on heuristic measures and/or make certain assumptions about the data and the model which are not representative of the real-world data and models. Further, most are designed without considering the usefulness by an end-user in a broader context. To address these issues, we present a notion of explanation fidelity based on Shapley values from cooperative game theory. We find that all of the investigated MLE explainability methods produce explanations that are incongruent with the ML model that is being explained. This is because they make critical assumptions about feature independence and linear feature interactions for computational reasons. We also find that in deployed, explanations are rarely used due to a variety of reason including that there are several other tools which are trusted more than the explanations and there is little incentive to use the explanations. In the cases when the explanations are used, we found that there is the danger that explanations persuade the end users to wrongly accept false positives and false negatives. However, ML model developers and maintainers find the explanations more useful to help ensure that the ML model does not have obvious biases. In light of these findings, we suggest a number of future directions including developing MLE methods that directly model non-linear model interactions and including design principles that take into account the usefulness of explanations to the end user. We also augment explanations with a set of trustworthiness measures that measure geometric aspects of the data to determine if the model output should be trusted.
Abstract not provided.
University partnerships play an essential role in sustaining Sandia’s vitality as a national laboratory. The SAA is an element of Sandia’s broader University Partnerships program, which facilitates recruiting and research collaborations with dozens of universities annually. The SAA program has two three-year goals. SAA aims to realize a step increase in hiring results, by growing the total annual inexperienced hires from each out-of-state SAA university. SAA also strives to establish and sustain strategic research partnerships by establishing several federally sponsored collaborations and multi-institutional consortiums in science & technology (S&T) priorities such as autonomy, advanced computing, hypersonics, quantum information science, and data science. The SAA program facilitates access to talent, ideas, and Research & Development facilities through strong university partnerships. Earlier this year, the SAA program and campus executives hosted John Myers, Sandia’s former Senior Director of Human Resources (HR) and Communications, and senior-level staff at Georgia Tech, U of Illinois, Purdue, UNM, and UT Austin. These campus visits provided an opportunity to share the history of the partnerships from the university leadership, tours of research facilities, and discussions of ongoing technical work and potential recruiting opportunities. These visits also provided valuable feedback to HR management that will help Sandia realize a step increase in hiring from SAA schools. The 2020-2021 Collaboration Report is a compilation of accomplishments in 2020 and 2021 from SAA and Sandia’s valued SAA university partners.
Abstract not provided.
Abstract not provided.
Abstract not provided.
Abstract not provided.
Abstract not provided.
Abstract not provided.
Abstract not provided.
Abstract not provided.
National security missions require understanding third-party software binaries, a key element of which is reasoning about how data flows through a program. However, vulnerability analysts protecting software lack adequate tools for understanding data flow in binaries. To reduce the human time burden for these analysts, we used human factors methods in a rolling discovery process to derive user-centric visual representation requirements. We encountered three main challenges: analysis projects span weeks, analysis goals significantly affect approaches and required knowledge, and analyst tools, techniques, conventions, and prioritization are based on personal preference. To address these challenges, we initially focused our human factors methods on an attack surface characterization task. We generalized our results using a two-stage modified sorting task, creating requirements for a data flow visualization. We implemented these requirements partially in manual static visualizations, which we informally evaluated, and partially in automatically generated interactive visualizations, which have yet to be integrated into workflows for evaluation. Our observations and results indicate that 1) this data flow visualization has the potential to enable novel code navigation, information presentation, and information sharing, and 2) it is an excellent time to pursue research applying human factors methods to binary analysis workflows.