In recent years, eye-tracking data have been frequently used for precise modeling of user states, including cognitive load, physical load, and cybersickness in virtual reality (VR). However, these data can also expose sensitive biometric and behavioral signatures of the users that allow for re-identification and the inference of sensitive demographics via linkage attacks. Existing privacy-preserving methods (e.g., differential privacy, federated learning, data anonymization, etc.) often compromise the fidelity of user state estimation, creating a research gap in balancing privacy with application utility. To address this, we propose a novel model that mitigates privacy leakage from eye-tracking data while preserving high accuracy in user state prediction. Our approach ranks eye-tracking features by their contribution to prediction and applies selective perturbation to high-risk features. Experimental results show significant reductions in demographic inference accuracy (gender: 95.4% to 60.0%, race: 86.3% to 49.7%, age: 76.3% to 55.3%), with only a 9.7% average accuracy drop for cognitive load, physical load, and cybersickness classification. Compared to a local differential privacy baseline, our method achieves higher utility preservation and stronger demographic suppression, yielding improvements of 19.1%, 20.6%, and 18.3% for age, gender, and race, respectively. These findings validate the potential for privacy-aware modeling in VR systems and offer a scalable path toward ethical, secure, and high-performance deployment of eye-tracking technology in real-world applications.

Cybersickness, a motion sickness like discomfort, is a major barrier to the usability of virtual reality (VR) systems. While prior work has focused mainly on predicting cybersickness severity, practical mitigation requires not only detecting how sick a user feels but also deciding whether a countermeasure is beneficial and determining its appropriate intensity. In this paper, we propose a two phase multitask learning framework that jointly models cybersickness severity, blur effectiveness, and blur intensity. In Phase 1, we pretrain temporal deep learning backbones on two single label datasets with only severity annotations. In Phase 2, we pro-gressively finetune the models on a multi-label dataset containing severity, blur effectiveness, and blur level labels. We evaluate three backbone architectures a Time-Series Transformer, Deep Temporal Convolutional Network, and TS-Mamba under a 10-fold block aware cross validation scheme. Results show that two phase training significantly outperforms single phase baselines, with the Time Series Transformer achieving best performance (FMS MAE = 0.57, R2 = 0.87; Blur Level MAE = 0.49, 2 = 0.95; Blur Preference ACC = 99.5%). Unlike prior rule based reduction frameworks that rely on static heuristics, our approach provides a data-driven "detect-decide-dose" pipeline that adapts blur mitigation dynamically to individual users. This demonstrates that single label pre-training is an effective strategy for developing multitask VR safety models under limited labeled data. To our knowledge, this is the first framework that unifies cybersickness prediction and adaptive reduction in a single model.

Cybersickness, characterized by discomforts such as dizziness, nausea, and eye strain, remains a significant barrier to the widespread adoption of virtual reality (VR). Recent research have proposed supervised machine learning models to predict the onset of cybersickness; however, these approaches depend heavily on labeled datasets. Acquiring labeled datasets typically necessitates time-consuming and resource-intensive user studies, limiting the feasibility of these supervised methods for consumer-level VR applications where obtaining labeled user data during use is impractical. Moreover, due to individual differences, often these datasets are not generalizable in consumer VR use. To address these limitations, we propose a novel semi-supervised learning framework for predicting cybersickness (i.e., Fast Motion Sickness (FMS)) using eye tracking, heart rate, and galvanic skin response data. Our proposed semi-supervised approach uses pseudo-labeling techniques (i.e., Self-training, Label Propagation, and Label Spreading) fused with temporal deep learning models (i.e., DeepTCN, CNN-LSTM, Transformers, LSTM). We evaluated our approach on three public cybersickness datasets (i.e., Bumpy Ride, Simulation 21, Maze) and our proposed semi-supervised approach demonstrates strong cybersickness predictive performance using only$1-5 {\%}$labeled data (i.e.,$95-99 {\%}$data remains unlabeled). Notably, the self-training approach with a DeepTCN model achieved an accuracy of$\mathbf{7 5. 8 6 \%}$in FMS prediction, outperforming the other models and pseudolabeling approaches. Our findings establish the viability of semisupervised learning for cybersickness prediction with minimally labeled datasets, paving the way for more practical and potentially generalizable cybersickness prediction systems in consumer VR applications.

Cybersickness remains a major challenge in virtual and mixed reality (VR/MR), yet existing methods primarily focus on predicting its onset without offering formal guarantees regarding its occurrence or effective mitigation. As VR/MR applications expand into safety-critical domains like healthcare, defense, verifiable safety assurances become essential to protect users from adverse physiological and psychological effects. This paper introduces a probabilistic verification framework leveraging Bayesian Networks (BN) to explicitly model the interactions among system parameters, human physiological responses, and cybersickness severity. Unlike deep learning approaches that lack interpretability and formal verification capabilities, the proposed BN model explicitly captures how environmental and system-level factors (e.g., luminance, spectral entropy, and image gradient complexity via HoG features) influence physiological responses (e.g., heart rate, reaction time, eye tracking), ultimately affecting cybersickness severity. By learning the joint probability distribution of these factors, our approach provides rigorous formal guarantees on cybersickness risk under specified operational conditions. If these guarantees are not met, automated adaptive adjustments are recommended to restore safe conditions. Experimental validation involving physiological and systemlevel data demonstrates that Bayesian Networks provide an interpretable and efficient framework, uniquely enabling formal probabilistic verification of cybersickness risks. This capability makes the proposed approach particularly suitable for designing and deploying VR/MR systems with explicitly verified safety constraints.

Augmented reality (AR) systems are increasingly deployed in tactical environments, but their reliance on seamless human-computer interaction makes them vulnerable to cognitive attacks that manipulate a user's perception and severely compromise user decisionmaking. To address this challenge, we introduce the Perception Graph, a novel model designed to reason about human perception within these systems. Our model operates by first mimicking the human process of interpreting key information from an MR environment and then representing the outcomes using a semantically meaningful structure. We demonstrate how the model can compute a quantitative score that reflects the level of perception distortion, providing a robust and measurable method for detecting and analyzing the effects of such cognitive attacks.

Cognitive attacks in mixed reality (MR), e.g., latency perturbations that induce frame-time jitter, can divert visual attention and degrade task performance. We study 2D gaze prediction under such disturbances and propose a time-aware sequence model that handles irregular sampling by supplying elapsed times Δt between observations and conditions on sparse event/object context available at prediction time via learned token embeddings. Using time-based windows, we evaluate within-user and cross-user temporal generalization on MR recordings spanning multiple attack intensities. Results indicate accurate, time-robust gaze regression under latency perturbations, supporting adaptive MR interfaces in adversarial settings.

Extended Reality (XR) systems are gaining widespread usability due to their impressive adaptability capabilities; yet, the critical challenge they face is user privacy. The subtle behavioral patterns revealed through human motion in XR environments serve as significant indicators that can be used to infer user characteristics. Accordingly, gender classification utilizing behavioral motion data has emerged as a critical research focus in this field. Traditional machine learning models have achieved success using gait or inertial data in surveillance and mobile applications. However, there is still limited work that targets XR-specific motion signals captured through headsets, controllers, and body tracking devices. The proposed interpretable framework, "YouKnowWho," aims to address this challenge by developing an explainable model for classifying gender from behavioral motion data. The framework consists of two sequential deep learning architectures: Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The performance of this framework is assessed using accuracy, precision, recall, and F1-score. Additionally, Integrated Gradients are used to analyze the importance of each feature in predicting gender. The results demonstrate that YouKnowWho is capable of classifying gender from behavioral motion data with a remarkable accuracy of 68.2%, and it can identify specific features that can be preserved or safeguarded to ensure user privacy.

Personal characteristics fundamentally shape virtual reality (VR) experiences, yet their integration into predictive models remains underexplored. This paper studies how to incorporate personal attributes (age, gender, prior VR experience) into Bayesian networks for cybersickness prediction via: (i) direct inclusion as root nodes, (ii) a two-stage model that learns a susceptibility score from personal attributes, and (iii) a stratified model. Using 26,040 samples from VR maze-navigation experiments, direct inclusion attains 82.53% accuracy (+14.02 percentage points over a 68.51% no-personal baseline). The two-stage approach reaches 77.32% while supporting cold-start prediction for unseen users, and stratified models achieve 73.62%. Using participant-level cross-validation to avoid subject leakage, we find that personalization consistently improves cybersickness prediction. These results argue that personal attributes should be treated as first-class signals in cybersickness models, with clear design trade-offs between maximal accuracy and deployability for unseen users, informing personalized VR systems and adaptive content delivery.

In recent cybersickness research, there has been a growing interest in predicting cybersickness using real-time physiological data such as heart rate, galvanic skin response, eye tracking, postural sway, and electroencephalogram. However, the impact of individual factors such as age and gender, which are pivotal in determining cybersickness susceptibility, remains unknown in predictive models. Our research seeks to address this gap, underscoring the necessity for a more personalized approach to cybersickness prediction to ensure a better, more inclusive virtual reality experience. We hypothesize that a personalized cybersickness prediction model would outperform non-personalized models in predicting cybersickness. Evaluating this, we explored four personalization techniques: 1) data grouping, 2) transfer learning, 3) early shaping, and 4) sample weighing using an open-source cybersickness dataset. Our empirical results indicate that personalized models significantly improve prediction accuracy. For instance, with early shaping, the Deep Temporal Convolutional Neural Network (DeepTCN) model achieved a 69.7% reduction in RMSE compared to its non-personalized version. Our study provides evidence of personalization techniques' benefits in improving cybersickness prediction. These findings have implications for developing personalized cybersickness prediction models tailored to individual differences, which can be used to develop personalized cybersickness reduction techniques in the future.

Cybersickness is a common ailment associated with virtual reality (VR) user experiences. Several automated methods exist based on machine learning (ML) and deep learning (DL) to detect cyber-sickness. However, most of these cybersickness detection methods are perceived as computationally intensive and black-box methods. Thus, those techniques are neither trustworthy nor practical for deploying on standalone energy-constrained VR head-mounted devices (HMDs). In this work, we present an explainable artificial intelligence (XAI)-based framework Lite VR for cybersickness detection, explaining the model's outcome, reducing the feature dimensions, and overall computational costs. First, we develop three cybersick-ness DL models based on long-term short-term memory (LSTM), gated recurrent unit (GRU), and multilayer perceptron (MLP). Then, we employed a post-hoc explanation, such as SHapley Additive Explanations (SHAP), to explain the results and extract the most dominant features of cybersickness. Finally, we retrain the DL models with the reduced number of features. Our results show that eye-tracking features are the most dominant for cybersickness detection. Furthermore, based on the XAI-based feature ranking and dimensionality reduction, we significantly reduce the model's size by up to 4.3×, training time by up to 5.6×, and its inference time by up to 3.8×, with higher cybersickness detection accuracy and low regression error (i.e., on Fast Motion Scale (FMS)). Our proposed lite LSTM model obtained an accuracy of 94% in classifying cyber-sickness and regressing (i.e., FMS 1–10) with a Root Mean Square Error (RMSE) of 0.30, which outperforms the state-of-the-art. Our proposed Lite VR framework can help researchers and practitioners analyze, detect, and deploy their DL-based cybersickness detection models in standalone VR HMDs.

A plethora of studies has been conducted to detect and reduce cybersickness in real-time. However, prior attempts to detect and minimize cybersickness after its onset may be ineffective as the onset tends to persist beyond its first occurrence. By forecasting the onset of cybersickness, it may be possible to mitigate the severity of cybersickness through earlier interventions. This research proposed a multimodal deep fusion approach to forecast cybersickness from the user’s physiological, head-tracking, and eye-tracking data. We proposed several hybrid multimodal deep fusion neural networks with Long short-term memory (LSTMs), Neural basis expansion analysis for interpretable time series forecasting(NBEATs) and Deep Temporal Convolutional Networks(DeepTCN) neural models to forecast cybersickness 30-60s in advance to its onset. To validate our proposed approach, we recruited 30 participants who were immersed in five virtual reality simulations. We collected eye-tracking, head-tracking, heart rate, and galvanic skin response data and used the fast-motion scale as ground truth. Our results suggest that the DeepTCN model with our proposed multimodal fusion network can forecast cybersickness onset 60 seconds in advance with a root-mean-square error of 0.49 (on a scale from 0-10). Furthermore, our results demonstrated that fusing eye tracking, heart rate, and galvanic skin response data outperformed other data fusion approaches. This research clarifies how early cybersickness can be forecast, paving the way for future research on early cybersickness mitigation approaches.

Cybersickness can be characterized by nausea, vertigo, headache, eye strain, and other discomforts when using virtual reality (VR) systems. The previously reported machine learning (ML) and deep learning (DL) algorithms for detecting (classification) and predicting (regression) VR cybersickness use black-box models; thus, they lack explainability. Moreover, VR sensors generate a massive amount of data, resulting in complex and large models. Therefore, having inherent explainability in cybersickness detection models can significantly improve the model’s trustworthiness and provide insight into why and how the ML/DL model amved at a specific decision. To address this issue, we present three explainable machine learning (xML) models to detect and predict cybersickness: 1) explainable boosting machine (EBM), 2) decision tree (DT), and 3) logistic regression (LR). We evaluate xML-based models with publicly available physiological and gameplay datasets for cybersickness. The results show that the EBM can detect cybersickness with an accuracy of 99.75% and 94.10% for the physiological and gameplay datasets, respectively. On the other hand, while predicting the cybersickness, EBM resulted in a Root Mean Square Error (RMSE) of 0.071 for the physiological dataset and 0.27 for the gameplay dataset. Furthermore, the EBM-based global explanation reveals exposure length, rotation, and acceleration as key features causing cybersickness in the gameplay dataset. In contrast, galvanic skin responses and heart rate are most significant in the physiological dataset. Our results also suggest that EBM-based local explanation can identify cybersickness-causing factors for individual samples. We believe the proposed xML-based cybersickness detection method can help future researchers understand, analyze, and design simpler cybersickness detection and reduction models.

Cybersickness prediction is one of the significant research challenges for real-time cybersickness reduction. Researchers have proposed different approaches for predicting cybersickness from bio-physiological data (e.g., heart rate, breathing rate, electroencephalogram). However, collecting bio-physiological data often requires external sensors, limiting locomotion and 3D-object manipulation during the virtual reality (VR) experience. Limited research has been done to predict cybersickness from the data readily available from the integrated sensors in head-mounted displays (HMDs) (e.g., head-tracking, eye-tracking, motion features), allowing free locomotion and 3D-object manipulation. This research proposes a novel deep fusion network to predict cybersickness severity from heterogeneous data readily available from the integrated HMD sensors. We extracted 1755 stereoscopic videos, eye-tracking, and head-tracking data along with the corresponding self-reported cybersickness severity collected from 30 participants during their VR gameplay. We applied several deep fusion approaches with the heterogeneous data collected from the participants. Our results suggest that cybersickness can be predicted with an accuracy of 87.77% and a root-mean-square error of 0.51 when using only eye-tracking and head-tracking data. We concluded that eye-tracking and head-tracking data are well suited for a standalone cybersickness prediction framework.

Cybersickness is one of the primary challenges to the usability and acceptability of virtual reality (VR). Cybersickness can cause motion sickness-like discomforts, including disorientation, headache, nausea, and fatigue, both during and after the VR immersion. Prior research suggested a significant correlation between physiological signals and cybersickness severity, as measured by the simulator sickness questionnaire (SSQ). However, SSQ may not be suitable for automatic detection of cybersickness severity during immersion, as it is usually reported before and after the immersion. In this study, we introduced an automated approach for the detection and prediction of cybersickness severity from the user's physiological signals. We collected heart rate, breathing rate, heart rate variability, and galvanic skin response data from 31 healthy participants while immersed in a VR roller coaster simulation. We found a significant difference in the participants' physiological signals during their cybersickness state compared to their resting baseline. We compared a support vector machine classifier and three deep neural classifiers for cybersickness severity detection and prediction in two minutes' future, given the previous two minutes of physiological signals. Our proposed simplified convolutional long short-term memory classifier achieved an accuracy of 97.44% for detecting current cybersickness severity and 87.38% for predicting future cybersickness severity from the physiological signals.