CyberSec Research

Effective teamwork is essential across diverse domains. During the team formation stage, a key challenge is forming teams that effectively balance user preferences with task objectives to enhance overall team satisfaction. In the team performing stage, maintaining cohesion and engagement is critical for sustaining high team performance. However, existing computational tools and algorithms for team optimization often rely on static data inputs, narrow algorithmic objectives, or solutions tailored for specific contexts, failing to account for the dynamic interplay of team members personalities, evolving goals, and changing individual preferences. Therefore, teams may encounter member dissatisfaction, as purely algorithmic assignments can reduce members commitment to team goals or experience suboptimal engagement due to the absence of timely, personalized guidance to help members adjust their behaviors and interactions as team dynamics evolve. Ultimately, these challenges can lead to reduced overall team performance. My Ph.D. dissertation aims to develop AI-augmented team optimization frameworks and practical systems that enhance team satisfaction, engagement, and performance. First, I propose a team formation framework that leverages a multi-armed bandit algorithm to iteratively refine team composition based on user preferences, ensuring alignment between individual needs and collective team goals to enhance team satisfaction. Second, I introduce tAIfa (Team AI Feedback Assistant), an AI-powered system that utilizes large language models (LLMs) to deliver immediate, personalized feedback to both teams and individual members, enhancing cohesion and engagement. Finally, I present PuppeteerLLM, an LLM-based simulation framework that simulates multi-agent teams to model complex team dynamics within realistic environments, incorporating task-driven collaboration and long-term coordination.

As a Ph.D. student with a diverse background in both public and private sectors, I have encountered numerous challenges in cross-disciplinary and multi-stakeholder team projects. My research on developing team compositions that involve multidisciplinary members from fields including education, academia, and health. Along with my advisor, we are focused on exploring how HCI can help individuals assemble more effective teams. This effort involves developing socio-technical systems that guide and inform individuals of the potential teams that they can assemble. We employ state-of-the-art algorithms that prioritize inclusion among team members from diverse areas of expertise and familiarity between the team members. Our goal for attending this workshop is to engage in meaningful dialogues with scholars and researchers, leveraging these interactions to refine our approach to building an AI-driven team composition system to foster effective, interdisciplinary collaboration in health-focused HCI research.

Maintaining an active lifestyle is vital for quality of life, yet challenging for wheelchair users. For instance, powered wheelchairs face increasing risks of obesity and deconditioning due to inactivity. Conversely, manual wheelchair users, who propel the wheelchair by pushing the wheelchair's handrims, often face upper extremity injuries from repetitive motions. These challenges underscore the need for a mobility system that promotes activity while minimizing injury risk. Maintaining optimal exertion during wheelchair use enhances health benefits and engagement, yet the variations in individual physiological responses complicate exertion optimization. To address this, we introduce PulseRide, a novel wheelchair system that provides personalized assistance based on each user's physiological responses, helping them maintain their physical exertion goals. Unlike conventional assistive systems focused on obstacle avoidance and navigation, PulseRide integrates real-time physiological data-such as heart rate and ECG-with wheelchair speed to deliver adaptive assistance. Using a human-in-the-loop reinforcement learning approach with Deep Q-Network algorithm (DQN), the system adjusts push assistance to keep users within a moderate activity range without under- or over-exertion. We conducted preliminary tests with 10 users on various terrains, including carpet and slate, to assess PulseRide's effectiveness. Our findings show that, for individual users, PulseRide maintains heart rates within the moderate activity zone as much as 71.7 percent longer than manual wheelchairs. Among all users, we observed an average reduction in muscle contractions of 41.86 percent, delaying fatigue onset and enhancing overall comfort and engagement. These results indicate that PulseRide offers a healthier, adaptive mobility solution, bridging the gap between passive and physically taxing mobility options.

Artificial intelligence promises to revolutionise medicine, yet its impact remains limited because of the pervasive translational gap. We posit that the prevailing technology-centric approaches underpin this challenge, rendering such systems fundamentally incompatible with clinical practice, specifically diagnostic reasoning and decision making. Instead, we propose a novel sociotechnical conceptualisation of data-driven support tools designed to complement doctors' cognitive and epistemic activities. Crucially, it prioritises real-world impact over superhuman performance on inconsequential benchmarks.

As one of the first research teams with full access to Siemens' Cinematic Reality, we evaluate its usability and clinical potential for cinematic volume rendering on the Apple Vision Pro. We visualized venous-phase liver computed tomography and magnetic resonance cholangiopancreatography scans from the CHAOS and MRCP\_DLRecon datasets. Fourteen medical experts assessed usability and anticipated clinical integration potential using the System Usability Scale, ISONORM 9242-110-S questionnaire, and an open-ended survey. Their feedback identified feasibility, key usability strengths, and required features to catalyze the adaptation in real-world clinical workflows. The findings provide insights into the potential of immersive cinematic rendering in medical imaging.

We propose a method that enables large language models (LLMs) to control embodied agents by directly mapping continuous observation vectors to continuous action vectors. Initially, the LLMs generate a control strategy based on a textual description of the agent, its environment, and the intended goal. This strategy is then iteratively refined through a learning process in which the LLMs are repeatedly prompted to improve the current strategy, using performance feedback and sensory-motor data collected during its evaluation. The method is validated on classic control tasks from the Gymnasium library and the inverted pendulum task from the MuJoCo library. In most cases, it successfully identifies optimal or high-performing solutions by integrating symbolic knowledge derived through reasoning with sub-symbolic sensory-motor data gathered as the agent interacts with its environment.

Online reviews have become an integral aspect of consumer decision-making on e-commerce websites, especially in the restaurant industry. Unlike sighted users who can visually skim through the reviews, perusing reviews remains challenging for blind users, who rely on screen reader assistive technology that supports predominantly one-dimensional narration of content via keyboard shortcuts. In an interview study, we uncovered numerous pain points of blind screen reader users with online restaurant reviews, notably, the listening fatigue and frustration after going through only the first few reviews. To address these issues, we developed QuickQue assistive tool that performs aspect-focused sentiment-driven summarization to reorganize the information in the reviews into an alternative, thematically-organized presentation that is conveniently perusable with a screen reader. At its core, QuickQue utilizes a large language model to perform aspect-based joint classification for grouping reviews, followed by focused summarizations within the groups to generate concise representations of reviewers' opinions, which are then presented to the screen reader users via an accessible interface. Evaluation of QuickQue in a user study with 10 participants showed significant improvements in overall usability and task workload compared to the status quo screen reader.

Medical imaging segmentation is essential in clinical settings for diagnosing diseases, planning surgeries, and other procedures. However, manual annotation is a cumbersome and effortful task. To mitigate these aspects, this study implements and evaluates the usability and clinical applicability of an extended reality (XR)-based segmentation tool for anatomical CT scans, using the Meta Quest 3 headset and Logitech MX Ink stylus. We develop an immersive interface enabling real-time interaction with 2D and 3D medical imaging data in a customizable workspace designed to mitigate workflow fragmentation and cognitive demands inherent to conventional manual segmentation tools. The platform combines stylus-driven annotation, mirroring traditional pen-on-paper workflows, with instant 3D volumetric rendering. A user study with a public craniofacial CT dataset demonstrated the tool's foundational viability, achieving a System Usability Scale (SUS) score of 66, within the expected range for medical applications. Participants highlighted the system's intuitive controls (scoring 4.1/5 for self-descriptiveness on ISONORM metrics) and spatial interaction design, with qualitative feedback highlighting strengths in hybrid 2D/3D navigation and realistic stylus ergonomics. While users identified opportunities to enhance task-specific precision and error management, the platform's core workflow enabled dynamic slice adjustment, reducing cognitive load compared to desktop tools. Results position the XR-stylus paradigm as a promising foundation for immersive segmentation tools, with iterative refinements targeting haptic feedback calibration and workflow personalization to advance adoption in preoperative planning.

AI music generation has advanced rapidly, with models like diffusion and autoregressive algorithms enabling high-fidelity outputs. These tools can alter styles, mix instruments, or isolate them. Since sound can be visualized as spectrograms, image-generation algorithms can be applied to generate novel music. However, these algorithms are typically trained on fixed datasets, which makes it challenging for them to interpret and respond to user input accurately. This is especially problematic because music is highly subjective and requires a level of personalization that image generation does not provide. In this work, we propose a human-computation approach to gradually improve the performance of these algorithms based on user interactions. The human-computation element involves aggregating and selecting user ratings to use as the loss function for fine-tuning the model. We employ a genetic algorithm that incorporates user feedback to enhance the baseline performance of a model initially trained on a fixed dataset. The effectiveness of this approach is measured by the average increase in user ratings with each iteration. In the pilot test, the first iteration showed an average rating increase of 0.2 compared to the baseline. The second iteration further improved upon this, achieving an additional increase of 0.39 over the first iteration.

Brain-Computer Interfaces (BCIs) based on motor imagery (MI) hold promise for restoring control in individuals with motor impairments. However, up to 30% of users remain unable to effectively use BCIs-a phenomenon termed ''BCI inefficiency.'' This study addresses a major limitation in current BCI training protocols: the use of fixed-length training paradigms that ignore individual learning variability. We propose a novel approach that leverages neuronal avalanches-spatiotemporal cascades of brain activity-as biomarkers to characterize and predict user-specific learning mechanism. Using electroencephalography (EEG) data collected across four MI-BCI training sessions in 20 healthy participants, we extracted two features: avalanche length and activations. These features revealed significant training and taskcondition effects, particularly in later sessions. Crucially, changes in these features across sessions ($\Delta$avalanche length and $\Delta$activations) correlated significantly with BCI performance and enabled prediction of future BCI success via longitudinal Support Vector Regression and Classification models. Predictive accuracy reached up to 91%, with notable improvements after spatial filtering based on selected regions of interest. These findings demonstrate the utility of neuronal avalanche dynamics as robust biomarkers for BCI training, supporting the development of personalized protocols aimed at mitigating BCI illiteracy.

In this work, we present a multi-tool evaluation of 106 deployed web-based chatbots, across domains like healthcare, education and customer service, comprising both standalone applications and embedded widgets using automated tools (Google Lighthouse, PageSpeed Insights, SiteImprove Accessibility Checker) and manual audits (Microsoft Accessibility Insights). Our analysis reveals that over 80% of chatbots exhibit at least one critical accessibility issue, and 45% suffer from missing semantic structures or ARIA role misuse. Furthermore, we found that accessibility scores correlate strongly across tools (e.g., Lighthouse vs PageSpeed Insights, r = 0.861), but performance scores do not (r = 0.436), underscoring the value of a multi-tool approach. We offer a replicable evaluation insights and actionable recommendations to support the development of user-friendly conversational interfaces.

Mediated by today's visual displays, information space allows users to discover, access and interact with a wide range of digital and physical information. The information presented in this space may be digital, physical or a blend of both, and appear across different dimensions - such as texts, images, 3D content and physical objects embedded within real-world environment. Navigating within the information space often involves interacting with mixed-dimensional entities, visually represented in both 2D and 3D. At times, interactions also involve transitioning among entities represented in different dimensions. We introduce the concept of mixed-dimensional information space, encompassing entities represented in both 2D and 3D. Interactions within the mixed-dimensional information space should be seamless and efficient: users should be able to focus on their primary tasks without being distracted by interactions with or transitions between entities. While incorporating 3D representations into the mixed-dimensional information space offers intuitive and immersive ways to interact with complex information, it is important to address potential seams and inefficiencies that arise while interacting with both 2D and 3D entities. This dissertation introduces new interactive techniques and systems to realize seamless and efficient interactions within the mixed-dimensional information space. This dissertation introduces three interactive systems: MemoVis which aims to use emergent generative AI to help users create reference images for 3D design feedback; PaperToPlace which demonstrates how paper-based instruction documents can be transformed and spatialized into a context-aware MR experience; and VRContour which explores how contour delineation workflow can be brought into VR.

Users of social media platforms based on recommendation systems (RecSys) (e.g. TikTok, X, YouTube) strategically interact with platform content to influence future recommendations. On some such platforms, users have been documented to form large-scale grassroots movements encouraging others to purposefully interact with algorithmically suppressed content in order to "boost" its recommendation; we term this behavior user altruism. To capture this behavior, we study a game between users and a RecSys, where users provide the RecSys (potentially manipulated) preferences over the contents available to them, and the RecSys -- limited by data and computation constraints -- creates a low-rank approximation preference matrix, and ultimately provides each user her (approximately) most-preferred item. We compare the users' social welfare under truthful preference reporting and under a class of strategies capturing user altruism. In our theoretical analysis, we provide sufficient conditions to ensure strict increases in user social welfare under user altruism, and provide an algorithm to find an effective altruistic strategy. Interestingly, we show that for commonly assumed recommender utility functions, effectively altruistic strategies also improve the utility of the RecSys! We show that our results are robust to several model misspecifications, thus strengthening our conclusions. Our theoretical analysis is complemented by empirical results of effective altruistic strategies on the GoodReads dataset, and an online survey on how real-world users behave altruistically in RecSys. Overall, our findings serve as a proof-of-concept of the reasons why traditional RecSys may incentivize users to form collectives and/or follow altruistic strategies when interacting with them.

In this paper, we investigate the challenges associated with using egocentric devices to photorealistic reconstruct the scene in high dynamic range. Existing methodologies typically assume using frame-rate 6DoF pose estimated from the device's visual-inertial odometry system, which may neglect crucial details necessary for pixel-accurate reconstruction. This study presents two significant findings. Firstly, in contrast to mainstream work treating RGB camera as global shutter frame-rate camera, we emphasize the importance of employing visual-inertial bundle adjustment (VIBA) to calibrate the precise timestamps and movement of the rolling shutter RGB sensing camera in a high frequency trajectory format, which ensures an accurate calibration of the physical properties of the rolling-shutter camera. Secondly, we incorporate a physical image formation model based into Gaussian Splatting, which effectively addresses the sensor characteristics, including the rolling-shutter effect of RGB cameras and the dynamic ranges measured by sensors. Our proposed formulation is applicable to the widely-used variants of Gaussian Splats representation. We conduct a comprehensive evaluation of our pipeline using the open-source Project Aria device under diverse indoor and outdoor lighting conditions, and further validate it on a Meta Quest3 device. Across all experiments, we observe a consistent visual enhancement of +1 dB in PSNR by incorporating VIBA, with an additional +1 dB achieved through our proposed image formation model. Our complete implementation, evaluation datasets, and recording profile are available at http://www.projectaria.com/photoreal-reconstruction/

Large Language Models (LLMs) offer novel opportunities for educational applications that have the potential to transform traditional learning for students. Despite AI-enhanced applications having the potential to provide personalized learning experiences, more studies are needed on the design of generative AI systems and evidence for using them in real educational settings. In this paper, we design, implement and evaluate \texttt{Reviewriter}, a novel tool to provide students with AI-generated instructions for writing peer reviews in German. Our study identifies three key aspects: a) we provide insights into student needs when writing peer reviews with generative models which we then use to develop a novel system to provide adaptive instructions b) we fine-tune three German language models on a selected corpus of 11,925 student-written peer review texts in German and choose German-GPT2 based on quantitative measures and human evaluation, and c) we evaluate our tool with fourteen students, revealing positive technology acceptance based on quantitative measures. Additionally, the qualitative feedback presents the benefits and limitations of generative AI in peer review writing.

AI-based interactive assistants are advancing human-augmenting technology, yet their effects on users' mental and physiological states remain under-explored. We address this gap by analyzing how Copilot for Microsoft Word, a LLM-based assistant, impacts users. Using tasks ranging from objective (SAT reading comprehension) to subjective (personal reflection), and with measurements including fNIRS, Empatica E4, NASA-TLX, and questionnaires, we measure Copilot's effects on users. We also evaluate users' performance with and without Copilot across tasks. In objective tasks, participants reported a reduction of workload and an increase in enjoyment, which was paired with objective performance increases. Participants reported reduced workload and increased enjoyment with no change in performance in a creative poetry writing task. However, no benefits due to Copilot use were reported in a highly subjective self-reflection task. Although no physiological changes were recorded due to Copilot use, task-dependent differences in prefrontal cortex activation offer complementary insights into the cognitive processes associated with successful and unsuccessful human-AI collaboration. These findings suggest that AI assistants' effectiveness varies with task type-particularly showing decreased usefulness in tasks that engage episodic memory-and presents a brain-network based hypothesis of human-AI collaboration.

Practicing conversations with large language models (LLMs) presents a promising alternative to traditional in-person language learning. However, most LLMs generate text at a near-native level of complexity, making them ill-suited for beginner learners (CEFR: A1-A2). In this paper, we investigate whether controllable generation techniques -- specifically modular methods that do not require model fine-tuning -- can adapt LLM outputs to better support absolute beginners. We evaluate these methods through both automatic metrics and a user study with university-level learners of Japanese. Our findings show that while prompting alone fails to control output difficulty, the use of future discriminators (Yang and Klein, 2021) significantly improves output comprehensibility (from 40.4\% to 84.3\%). We further introduce a novel token-level evaluation metric, Token Miss Rate (TMR), that quantifies the proportion of incomprehensible tokens per utterance and correlates strongly with human judgments. To support future research in AI-assisted language learning, we release our code, models, annotation tools, and dataset.

Large Language Models (LLMs) increasingly rely on Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) to align model responses with human preferences. While RLHF employs a reinforcement learning approach with a separate reward model, SFT uses human-curated datasets for supervised learning. Both approaches traditionally depend on small, vetted groups of annotators, making them costly, prone to bias, and limited in scalability. We propose an open, crowd-sourced fine-tuning framework that addresses these limitations by enabling broader feedback collection for SFT without extensive annotator training. Our framework promotes incentive fairness via a point-based reward system correlated with Shapley values and guides model convergence through iterative model updates. Our multi-model selection framework demonstrates up to a 55% reduction in target distance over single-model selection, enabling subsequent experiments that validate our point-based reward mechanism's close alignment with Shapley values (a well-established method for attributing individual contributions) thereby supporting fair and scalable participation.