Research Papers

Datasets play a key role in imparting advanced capabilities to artificial intelligence (AI) foundation models that can be adapted to various downstream tasks. These downstream applications can introduce both beneficial and harmful capabilities -- resulting in dual use AI foundation models, with various technical and regulatory approaches to monitor and manage these risks. However, despite the crucial role of datasets, responsible dataset design and ensuring data-centric safety and ethical practices have received less attention. In this study, we pro-pose responsible dataset design framework that encompasses various stages in the AI and dataset lifecycle to enhance safety measures and reduce the risk of AI misuse due to low quality, unsafe and unethical data content. This framework is domain agnostic, suitable for adoption for various applications and can promote responsible practices in dataset creation, use, and sharing to facilitate red teaming, minimize risks, and increase trust in AI models.

Rule-based models offer interpretability but struggle with complex data, while deep neural networks excel in performance yet lack transparency. This work investigates a neuro-symbolic rule learning neural network named RL-Net that learns interpretable rule lists through neural optimization, applied for the first time to radar-based hand gesture recognition (HGR). We benchmark RL-Net against a fully transparent rule-based system (MIRA) and an explainable black-box model (XentricAI), evaluating accuracy, interpretability, and user adaptability via transfer learning. Our results show that RL-Net achieves a favorable trade-off, maintaining strong performance (93.03% F1) while significantly reducing rule complexity. We identify optimization challenges specific to rule pruning and hierarchy bias and propose stability-enhancing modifications. Compared to MIRA and XentricAI, RL-Net emerges as a practical middle ground between transparency and performance. This study highlights the real-world feasibility of neuro-symbolic models for interpretable HGR and offers insights for extending explainable AI to edge-deployable sensing systems.

The security of printed circuit boards (PCBs) has become increasingly vital as supply chain vulnerabilities, including tampering, present significant risks to electronic systems. While detecting tampering on a PCB is the first step for verification, forensics is also needed to identify the modified component. One non-invasive and reliable PCB tamper detection technique with global coverage is the impedance characterization of a PCB's power delivery network (PDN). However, it is an open question whether one can use the two-dimensional impedance signatures for forensics purposes. In this work, we introduce a novel PCB forensics approach using explainable AI (XAI) on impedance signatures. Through extensive experiments, we replicate various PCB tamper events, generating a dataset used to develop an XAI algorithm capable of not only detecting tampering but also explaining why the algorithm makes a decision about whether a tamper event has happened. At the core of our XAI algorithm is a random forest classifier with an accuracy of 96.7%, sufficient to explain the algorithm's decisions. To understand the behavior of the classifier in the decision-making process, we utilized SHAP values as an XAI tool to determine which frequency component influences the classifier's decision for a particular class the most. This approach enhances detection capabilities as well as advancing the verifier's ability to reverse-engineer and analyze two-dimensional impedance signatures for forensics.

Composable Building Blocks for Controllable and Transparent Interactive AI Systems

Sebe Vanbrabant, Gustavo Rovelo Ruiz, Davy Vanacken

While the increased integration of AI technologies into interactive systems enables them to solve an equally increasing number of tasks, the black box problem of AI models continues to spread throughout the interactive system as a whole. Explainable AI (XAI) techniques can make AI models more accessible by employing post-hoc methods or transitioning to inherently interpretable models. While this makes individual AI models clearer, the overarching system architecture remains opaque. To this end, we propose an approach to represent interactive systems as sequences of structural building blocks, such as AI models and control mechanisms grounded in the literature. These can then be explained through accompanying visual building blocks, such as XAI techniques. The flow and APIs of the structural building blocks form an explicit overview of the system. This serves as a communication basis for both humans and automated agents like LLMs, aligning human and machine interpretability of AI models. We discuss a selection of building blocks and concretize our flow-based approach in an architecture and accompanying prototype interactive system.

As AI systems are increasingly tested and deployed in open-ended and high-stakes domains, crowdworkers are often tasked with responsible AI (RAI) content work. These tasks include labeling violent content, moderating disturbing text, or simulating harmful behavior for red teaming exercises to shape AI system behaviors. While prior research efforts have highlighted the risks to worker well-being associated with RAI content work, far less attention has been paid to how these risks are communicated to workers by task designers or individuals who design and post RAI tasks. Existing transparency frameworks and guidelines, such as model cards, datasheets, and crowdworksheets, focus on documenting model information and dataset collection processes, but they overlook an important aspect of disclosing well-being risks to workers. In the absence of standard workflows or clear guidance, the consistent application of content warnings, consent flows, or other forms of well-being risk disclosure remains unclear. This study investigates how task designers approach risk disclosure in crowdsourced RAI tasks. Drawing on interviews with 23 task designers across academic and industry sectors, we examine how well-being risk is recognized, interpreted, and communicated in practice. Our findings highlight the need to support task designers in identifying and communicating risks not only to support crowdworker well-being but also to strengthen the ethical integrity and technical efficacy of AI development pipelines.

This paper calls on the research community not only to investigate how human biases are inherited by large language models (LLMs) but also to explore how these biases in LLMs can be leveraged to make society's "unwritten code" - such as implicit stereotypes and heuristics - visible and accessible for critique. We introduce a conceptual framework through a case study in science: uncovering hidden rules in peer review - the factors that reviewers care about but rarely state explicitly due to normative scientific expectations. The idea of the framework is to push LLMs to speak out their heuristics through generating self-consistent hypotheses - why one paper appeared stronger in reviewer scoring - among paired papers submitted to 46 academic conferences, while iteratively searching deeper hypotheses from remaining pairs where existing hypotheses cannot explain. We observed that LLMs' normative priors about the internal characteristics of good science extracted from their self-talk, e.g., theoretical rigor, were systematically updated toward posteriors that emphasize storytelling about external connections, such as how the work is positioned and connected within and across literatures. Human reviewers tend to explicitly reward aspects that moderately align with LLMs' normative priors (correlation = 0.49) but avoid articulating contextualization and storytelling posteriors in their review comments (correlation = -0.14), despite giving implicit reward to them with positive scores. These patterns are robust across different models and out-of-sample judgments. We discuss the broad applicability of our proposed framework, leveraging LLMs as diagnostic tools to amplify and surface the tacit codes underlying human society, enabling public discussion of revealed values and more precisely targeted responsible AI.

AI-driven automation generates broad-based social benefit only if technical gains become visible, durable, and publicly claimable. We develop a policy-facing stress test by extending a standard task-automation growth model with an AI capability parameter that raises productivity on automatable tasks while holding the set of tasks fixed. The exercise is intentionally limited: it is not a forecast of AI timelines or a full welfare analysis, but a way to identify which institutions determine whether AI rents can support broad transfers. Calibrated to U.S. quantities, the model shows that capability alone is not decisive. Public capture, deployment costs, automation scope, and market structure jointly determine when AI gains become shareable. The main policy lesson is that moving from low to moderate public capture (33\%) can substitute for substantial AI capability growth, while pushing capture further to full nationalization yields smaller gains, especially if deployment or safety costs are high. Competition policy also has distributional consequences: opening concentrated AI markets may improve fairness and resilience, but can reduce the rent pool unless alternative public-claim institutions are built. Cross-nationally, tax-heavy systems lower the needed AI capability threshold through stronger effective revenue collection, while Singaporean and Abu Dhabi-style public-asset models show that governments can also capture AI gains through ownership and investment returns rather than taxes alone. Our framework therefore identifies which levers governments can act on now to make future AI gains easier to measure, claim, and distribute broadly.

The EU AI Act makes explainability urgent for high-risk AI systems, yet most XAI research focuses on technical metrics rather than regulatory compliance. Understanding how legal requirements reshape XAI method design is challenging: the AI Act regulates organizational relationships (providers, deployers) using legal terminology, specifies obligations without concrete technical requirements, and underrepresents end-users--the very stakeholders whose needs human-centered XAI addresses. As regulations emerge globally, human-centered XAI practitioners face both a challenge and an opportunity: regulations pull XAI research toward real-world deployment, while practitioners can actively shape how explainability enables compliance. This establishes a bidirectional relationship. Our contribution is threefold. First, we provide the first interdisciplinary analysis of XAI's role in the AI Act--conducted by a team comprising AI Act legal experts, ML engineers, and requirements engineers--on a real-world clinical decision support system. Second, we systematically align XAI stakeholder roles with AI Act legal responsibilities, revealing where explainability methods address regulatory requirements versus where additional measures are necessary. Third, we identify three key opportunities for human-centered XAI practitioners: actively defining their roles in regulatory implementation; making the user-to-affected-party relationship explicit where regulations address only provider-deployer obligations; and enabling compliance while building multi-level trust--from regulators to affected parties.

University students and working professionals are increasingly encountering generative artificial intelligence (AI) in education and practice, yet their approaches and outcomes differ markedly. This paper proposes an academic study contrasting novice over-reliance on AI with expert augmentation of AI, grounded in two real-world narratives. In one, a university student attempted to outsource learning entirely to AI, eschewing course engagement. In the other, seasoned cybersecurity professionals in the Tradewinds 2025 red/blue team exercise collaboratively employed AI tools to enhance (not replace) their domain expertise. This proposal outlines a comparative research design to investigate how students' perception of AI as a learning replacement versus professionals' use of AI as an expert tool impacts outcomes. Drawing on current literature in educational technology and workplace AI, we examine implications for curriculum design, AI literacy, and assessment reform in higher education. We hypothesize that blind reliance on AI can erode fundamental skills and academic integrity, whereas guided use of AI by knowledgeable users can amplify productivity without sacrificing quality. The paper details methodologies for classroom and workplace data collection, including student and professional surveys, interviews, and performance analyses. Anticipated findings aim to inform responsible AI integration in curricula, balancing innovation with the necessity of domain knowledge. We conclude with recommendations for pedagogical strategies, institutional policies to foster AI literacy, and a call for longitudinal studies tracking how AI usage during university affects professional competencies over time.

This paper elaborates on the concept of moral exercises as a means to help AI actors cultivate virtues that enable effective human oversight of AI systems. We explore the conceptual framework and significance of moral exercises, situating them within the contexts of philosophical discourse, ancient practices, and contemporary AI ethics scholarship. We outline the core pillars of the moral exercises methodology - eliciting an engaged personal disposition, fostering relational understanding, and cultivating technomoral wisdom - and emphasize their relevance to key activities and competencies essential for human oversight of AI systems. Our argument is supported by findings from three pilot studies involving a company, a multidisciplinary team of AI researchers, and higher education students. These studies allow us to explore both the potential and the limitations of moral exercises. Based on the collected data, we offer insights into how moral exercises can foster a responsible AI culture within organizations, and suggest directions for future research.

As machine learning is increasingly applied in an online fashion to deal with evolving data streams, the fairness of these algorithms is a matter of growing ethical and legal concern. In many use cases, class imbalance in the data also needs to be dealt with to ensure predictive performance. Current fairness-aware stream learners typically attempt to solve these issues through in- or post-processing by focusing on optimizing one specific discrimination metric, addressing class imbalance in a separate processing step. While C-SMOTE is a highly effective model-agnostic pre-processing approach to mitigate class imbalance, as a side effect of this method, algorithmic bias is often introduced. Therefore, we propose CFSMOTE - a fairness-aware, continuous SMOTE variant - as a pre-processing approach to simultaneously address the class imbalance and fairness concerns by employing situation testing and balancing fairness-relevant groups during oversampling. Unlike other fairness-aware stream learners, CFSMOTE is not optimizing for only one specific fairness metric, therefore avoiding potentially problematic trade-offs. Our experiments show significant improvement on several common group fairness metrics in comparison to vanilla C-SMOTE while maintaining competitive performance, also in comparison to other fairness-aware algorithms.

From What Ifs to Insights: Counterfactuals in Causal Inference vs. Explainable AI

Galit Shmueli, David Martens, Jaewon Yoo +1

Counterfactuals play a pivotal role in the two distinct data science fields of causal inference (CI) and explainable artificial intelligence (XAI). While the core idea behind counterfactuals remains the same in both fields--the examination of what would have happened under different circumstances--there are key differences in how they are used and interpreted. We introduce a formal definition that encompasses the multi-faceted concept of the counterfactual in CI and XAI. We then discuss how counterfactuals are used, evaluated, generated, and operationalized in CI vs. XAI, highlighting conceptual and practical differences. By comparing and contrasting the two, we hope to identify opportunities for cross-fertilization across CI and XAI.