CyberSec Research

Most adaptive AR storytelling systems define environmental semantics using simple object labels and spatial coordinates, limiting narratives to rigid, pre-defined logic. This oversimplification overlooks the contextual significance of object relationships-for example, a wedding ring on a nightstand might suggest marital conflict, yet is treated as just "two objects" in space. To address this, we explored integrating Vision Language Models (VLMs) into AR pipelines. However, several challenges emerged: First, stories generated with simple prompt guidance lacked narrative depth and spatial usage. Second, spatial semantics were underutilized, failing to support meaningful storytelling. Third, pre-generated scripts struggled to align with AR Foundation's object naming and coordinate systems. We propose a scene-driven AR storytelling framework that reimagines environments as active narrative agents, built on three innovations: 1. State-aware object semantics: We decompose object meaning into physical, functional, and metaphorical layers, allowing VLMs to distinguish subtle narrative cues between similar objects. 2. Structured narrative interface: A bidirectional JSON layer maps VLM-generated metaphors to AR anchors, maintaining spatial and semantic coherence. 3. STAM evaluation framework: A three-part experimental design evaluates narrative quality, highlighting both strengths and limitations of VLM-AR integration. Our findings show that the system can generate stories from the environment itself, not just place them on top of it. In user studies, 70% of participants reported seeing real-world objects differently when narratives were grounded in environmental symbolism. By merging VLMs' generative creativity with AR's spatial precision, this framework introduces a novel object-driven storytelling paradigm, transforming passive spaces into active narrative landscapes.

Conversational recommender systems (CRSs) provide users with an interactive means to express preferences and receive real-time personalized recommendations. The success of these systems is heavily influenced by the preference elicitation process. While existing research mainly focuses on what questions to ask during preference elicitation, there is a notable gap in understanding what role broader interaction patterns including tone, pacing, and level of proactiveness play in supporting users in completing a given task. This study investigates the impact of different conversational styles on preference elicitation, task performance, and user satisfaction with CRSs. We conducted a controlled experiment in the context of scientific literature recommendation, contrasting two distinct conversational styles, high involvement (fast paced, direct, and proactive with frequent prompts) and high considerateness (polite and accommodating, prioritizing clarity and user comfort) alongside a flexible experimental condition where users could switch between the two. Our results indicate that adapting conversational strategies based on user expertise and allowing flexibility between styles can enhance both user satisfaction and the effectiveness of recommendations in CRSs. Overall, our findings hold important implications for the design of future CRSs.

Alt-text is essential for mobile app accessibility, yet UI icons often lack meaningful descriptions, limiting accessibility for screen reader users. Existing approaches either require extensive labeled datasets, struggle with partial UI contexts, or operate post-development, increasing technical debt. We first conduct a formative study to determine when and how developers prefer to generate icon alt-text. We then explore the ALTICON approach for generating alt-text for UI icons during development using two fine-tuned models: a text-only large language model that processes extracted UI metadata and a multi-modal model that jointly analyzes icon images and textual context. To improve accuracy, the method extracts relevant UI information from the DOM tree, retrieves in-icon text via OCR, and applies structured prompts for alt-text generation. Our empirical evaluation with the most closely related deep-learning and vision-language models shows that ALTICON generates alt-text that is of higher quality while not requiring a full-screen input.

Ensuring equitable access to computing education for all students-including those with autism, dyslexia, or ADHD-is essential to developing a diverse and inclusive workforce. To understand the state of disability research in computing education, we conducted a systematic literature review of research on neurodiversity in computing education. Our search resulted in 1,943 total papers, which we filtered to 14 papers based on our inclusion criteria. Our mixed-methods approach analyzed research methods, participants, contribution types, and findings. The three main contribution types included empirical contributions based on user studies (57.1%), opinion contributions and position papers (50%), and survey contributions (21.4%). Interviews were the most common methodology (75% of empirical contributions). There were often inconsistencies in how research methods were described (e.g., number of participants and interview and survey materials). Our work shows that research on neurodivergence in computing education is still very preliminary. Most papers provided curricular recommendations that lacked empirical evidence to support those recommendations. Three areas of future work include investigating the impacts of active learning, increasing awareness and knowledge about neurodiverse students' experiences, and engaging neurodivergent students in the design of pedagogical materials and computing education research.

This paper presents a novel research analytical IT system grounded in Martin Heidegger's Fundamental Ontology, distinguishing between beings (das Seiende) and Being (das Sein). The system employs two modally distinct, descriptively complete languages: a categorical language of beings for processing user inputs and an existential language of Being for internal analysis. These languages are bridged via a phenomenological reduction module, enabling the system to analyze user queries (including questions, answers, and dialogues among IT specialists), identify recursive and self-referential structures, and provide actionable insights in categorical terms. Unlike contemporary systems limited to categorical analysis, this approach leverages Heidegger's phenomenological existential analysis to uncover deeper ontological patterns in query processing, aiding in resolving logical traps in complex interactions, such as metaphor usage in IT contexts. The path to full realization involves formalizing the language of Being by a research team based on Heidegger's Fundamental Ontology; given the existing completeness of the language of beings, this reduces the system's computability to completeness, paving the way for a universal query analysis tool. The paper presents the system's architecture, operational principles, technical implementation, use cases--including a case based on real IT specialist dialogues--comparative evaluation with existing tools, and its advantages and limitations.

Personalized support is essential to fulfill individuals' emotional needs and sustain their mental well-being. Large language models (LLMs), with great customization flexibility, hold promises to enable individuals to create their own emotional support agents. In this work, we developed ChatLab, where users could construct LLM-powered chatbots with additional interaction features including voices and avatars. Using a Research through Design approach, we conducted a week-long field study followed by interviews and design activities (N = 22), which uncovered how participants created diverse chatbot personas for emotional reliance, confronting stressors, connecting to intellectual discourse, reflecting mirrored selves, etc. We found that participants actively enriched the personas they constructed, shaping the dynamics between themselves and the chatbot to foster open and honest conversations. They also suggested other customizable features, such as integrating online activities and adjustable memory settings. Based on these findings, we discuss opportunities for enhancing personalized emotional support through emerging AI technologies.

Large Language Models (LLMs) are increasingly being used for automated evaluations and explaining them. However, concerns about explanation quality, consistency, and hallucinations remain open research challenges, particularly in high-stakes contexts like privacy and security, where user trust and decision-making are at stake. In this paper, we investigate these issues in the context of PRISMe, an interactive privacy policy assessment tool that leverages LLMs to evaluate and explain website privacy policies. Based on a prior user study with 22 participants, we identify key concerns regarding LLM judgment transparency, consistency, and faithfulness, as well as variations in user preferences for explanation detail and engagement. We discuss potential strategies to mitigate these concerns, including structured evaluation criteria, uncertainty estimation, and retrieval-augmented generation (RAG). We identify a need for adaptive explanation strategies tailored to different user profiles for LLM-as-a-judge. Our goal is to showcase the application area of usable privacy and security to be promising for Human-Centered Explainable AI (HCXAI) to make an impact.

The rapid evolution of artificial intelligence (AI) has introduced AI agents as a disruptive paradigm across various industries, yet their application in machine translation (MT) remains underexplored. This paper describes and analyses the potential of single- and multi-agent systems for MT, reflecting on how they could enhance multilingual digital communication. While single-agent systems are well-suited for simpler translation tasks, multi-agent systems, which involve multiple specialized AI agents collaborating in a structured manner, may offer a promising solution for complex scenarios requiring high accuracy, domain-specific knowledge, and contextual awareness. To demonstrate the feasibility of multi-agent workflows in MT, we are conducting a pilot study in legal MT. The study employs a multi-agent system involving four specialized AI agents for (i) translation, (ii) adequacy review, (iii) fluency review, and (iv) final editing. Our findings suggest that multi-agent systems may have the potential to significantly improve domain-adaptability and contextual awareness, with superior translation quality to traditional MT or single-agent systems. This paper also sets the stage for future research into multi-agent applications in MT, integration into professional translation workflows, and shares a demo of the system analyzed in the paper.

Industrial dashboards, commonly deployed by organizations such as enterprises and governments, are increasingly crucial in data communication and decision-making support across various domains. Designing an industrial dashboard prototype is particularly challenging due to its visual complexity, which can include data visualization, layout configuration, embellishments, and animations. Additionally, in real-world industrial settings, designers often encounter numerous constraints. For instance, when companies negotiate collaborations with clients and determine design plans, they typically need to demo design prototypes and iterate on them based on mock data quickly. Such a task is very common and crucial during the ideation stage, as it not only helps save developmental costs but also avoids data-related issues such as lengthy data handover periods. However, existing authoring tools of dashboards are mostly not tailored to such prototyping needs, and motivated by these gaps, we propose DashChat, an interactive system that leverages large language models (LLMs) to generate industrial dashboard design prototypes from natural language. We collaborated closely with designers from the industry and derived the requirements based on their practical experience. First, by analyzing 114 high-quality industrial dashboards, we summarized their common design patterns and inject the identified ones into LLMs as reference. Next, we built a multi-agent pipeline powered by LLMs to understand textual requirements from users and generate practical, aesthetic prototypes. Besides, functionally distinct, parallel-operating agents are created to enable efficient generation. Then, we developed a user-friendly interface that supports text-based interaction for generating and modifying prototypes. Two user studies demonstrated that our system is both effective and efficient in supporting design prototyping.

Decision-makers run the risk of relying too much on machine recommendations. Explainable AI, a common strategy for calibrating reliance, has mixed and even negative effects, such as increasing overreliance. To cognitively engage the decision-maker and to facilitate a deliberate decision-making process, we propose a potential `reflection machine' that supports critical reflection about the pending decision, including the machine recommendation. Reflection has been shown to improve critical thinking and reasoning, and thus decision-making. One way to stimulate reflection is to ask relevant questions. To systematically create questions, we present a question taxonomy inspired by Socratic questions and human-centred explainable AI. This taxonomy can contribute to the design of such a `reflection machine' that asks decision-makers questions. Our work is part of the growing research on human-machine collaborations that goes beyond the paradigm of machine recommendations and explanations, and aims to enable greater human oversight as required by the European AI Act.

This study explored how large language models (LLMs) perform in two areas related to art: writing critiques of artworks and reasoning about mental states (Theory of Mind, or ToM) in art-related situations. For the critique generation part, we built a system that combines Noel Carroll's evaluative framework with a broad selection of art criticism theories. The model was prompted to first write a full-length critique and then shorter, more coherent versions using a step-by-step prompting process. These AI-generated critiques were then compared with those written by human experts in a Turing test-style evaluation. In many cases, human subjects had difficulty telling which was which, and the results suggest that LLMs can produce critiques that are not only plausible in style but also rich in interpretation, as long as they are carefully guided. In the second part, we introduced new simple ToM tasks based on situations involving interpretation, emotion, and moral tension, which can appear in the context of art. These go beyond standard false-belief tests and allow for more complex, socially embedded forms of reasoning. We tested 41 recent LLMs and found that their performance varied across tasks and models. In particular, tasks that involved affective or ambiguous situations tended to reveal clearer differences. Taken together, these results help clarify how LLMs respond to complex interpretative challenges, revealing both their cognitive limitations and potential. While our findings do not directly contradict the so-called Generative AI Paradox--the idea that LLMs can produce expert-like output without genuine understanding--they suggest that, depending on how LLMs are instructed, such as through carefully designed prompts, these models may begin to show behaviors that resemble understanding more closely than we might assume.

Human error remains a critical concern in aviation safety, contributing to 70-80% of accidents despite technological advancements. While physiological measures show promise for error detection in laboratory settings, their effectiveness in dynamic flight environments remains underexplored. Through live flight trials with nine commercial pilots, we investigated whether established error-detection approaches maintain accuracy during actual flight operations. Participants completed standardized multi-tasking scenarios across conditions ranging from laboratory settings to straight-and-level flight and 2G manoeuvres while we collected synchronized physiological data. Our findings demonstrate that EEG-based classification maintains high accuracy (87.83%) during complex flight manoeuvres, comparable to laboratory performance (89.23%). Eye-tracking showed moderate performance (82.50\%), while ECG performed near chance level (51.50%). Classification accuracy remained stable across flight conditions, with minimal degradation during 2G manoeuvres. These results provide the first evidence that physiological error detection can translate effectively to operational aviation environments.

Seniors represent a growing user base for mobile applications; however, many apps fail to adequately address their accessibility challenges and usability preferences. To investigate this issue, we conducted an exploratory focus group study with 16 senior participants, from which we derived an initial set of user personas highlighting key accessibility and personalisation barriers. These personas informed the development of a model-driven engineering toolset, which was used to generate adaptive mobile app prototypes tailored to seniors' needs. We then conducted a second focus group study with 22 seniors to evaluate these prototypes and validate our findings. Based on insights from both studies, we developed a refined set of personas and a series of accessibility and personalisation recommendations grounded in empirical data, prior research, accessibility standards, and developer resources, aimed at supporting software practitioners in designing more inclusive mobile applications.

Drivers' perception of risk determines their acceptance, trust, and use of the Automated Driving Systems (ADSs). However, perceived risk is subjective and difficult to evaluate using existing methods. To address this issue, a driver's subjective perceived risk (DSPR) model is proposed, regarding perceived risk as a dynamically triggered mechanism with anisotropy and attenuation. 20 participants are recruited for a driver-in-the-loop experiment to report their real-time subjective risk ratings (SRRs) when experiencing various automatic driving scenarios. A convolutional neural network and bidirectional long short-term memory network with temporal pattern attention (CNN-Bi-LSTM-TPA) is embedded into a semi-supervised learning strategy to predict SRRs, aiming to reduce data noise caused by subjective randomness of participants. The results illustrate that DSPR achieves the highest prediction accuracy of 87.91% in predicting SRRs, compared to three state-of-the-art risk models. The semi-supervised strategy improves accuracy by 20.12%. Besides, CNN-Bi-LSTM-TPA network presents the highest accuracy among four different LSTM structures. This study offers an effective method for assessing driver's perceived risk, providing support for the safety enhancement of ADS and driver's trust improvement.

Enhancing emotional well-being has become a significant focus in HCI and CSCW, with technologies increasingly designed to track, visualize, and manage emotions. However, these approaches have faced criticism for potentially suppressing certain emotional experiences. Through a scoping review of 53 empirical studies from ACM proceedings implementing Technology-Mediated Emotion Intervention (TMEI), we critically examine current practices through lenses drawn from HCI critical theories. Our analysis reveals emotion intervention mechanisms that extend beyond traditional emotion regulation paradigms, identifying care-centered goals that prioritize non-judgmental emotional support and preserve users' identities. The findings demonstrate how researchers design technologies for generating artificial care, intervening in power dynamics, and nudging behavioral changes. We contribute the concept of "emotion support" as an alternative approach to "emotion regulation," emphasizing human-centered approaches to emotional well-being. This work advances the understanding of diverse human emotional needs beyond individual and cognitive perspectives, offering design implications that critically reimagine how technologies can honor emotional complexity, preserve human agency, and transform power dynamics in care contexts.

Learning is an active process that is deeply tied to physical and social contexts. Yet schools traditionally place learners in a passive role and focus on decontextualizing knowledge. Situating learning in more authentic tasks and contexts typically requires taking it outside the classroom via field trips and apprenticeships, but virtual reality (VR) is a promising tool to bring more authentically situated learning experiences into classrooms. In this position paper, I discuss how one of VR's primary affordances for learning is heightening agenct, and how such heightened agency can facilitate more authenticlaly situated learning by allowing learners legitimate peripheral participation.

In this paper, we advance the study of AI-augmented reasoning in the context of Human-Computer Interaction (HCI), psychology and cognitive science, focusing on the critical task of visual perception. Specifically, we investigate the applicability of Multimodal Large Language Models (MLLMs) in this domain. To this end, we leverage established principles and explanations from psychology and cognitive science related to complexity in human visual perception. We use them as guiding principles for the MLLMs to compare and interprete visual content. Our study aims to benchmark MLLMs across various explainability principles relevant to visual perception. Unlike recent approaches that primarily employ advanced deep learning models to predict complexity metrics from visual content, our work does not seek to develop a mere new predictive model. Instead, we propose a novel annotation-free analytical framework to assess utility of MLLMs as cognitive assistants for HCI tasks, using visual perception as a case study. The primary goal is to pave the way for principled study in quantifying and evaluating the interpretability of MLLMs for applications in improving human reasoning capability and uncovering biases in existing perception datasets annotated by humans.

There has been a continued trend towards minimizing instrumentation for full-body motion capture, going from specialized rooms and equipment, to arrays of worn sensors and recently sparse inertial pose capture methods. However, as these techniques migrate towards lower-fidelity IMUs on ubiquitous commodity devices, like phones, watches, and earbuds, challenges arise including compromised online performance, temporal consistency, and loss of global translation due to sensor noise and drift. Addressing these challenges, we introduce MobilePoser, a real-time system for full-body pose and global translation estimation using any available subset of IMUs already present in these consumer devices. MobilePoser employs a multi-stage deep neural network for kinematic pose estimation followed by a physics-based motion optimizer, achieving state-of-the-art accuracy while remaining lightweight. We conclude with a series of demonstrative applications to illustrate the unique potential of MobilePoser across a variety of fields, such as health and wellness, gaming, and indoor navigation to name a few.