As extended reality (XR) systems become increasingly immersive and sensor-rich, they enable the collection of behavioral signals such as eye and body telemetry. These signals support personalized and responsive experiences and may also contain unique patterns that can be linked back to individuals. However, privacy mechanisms that naively pair unimodal mechanisms (e.g., independently apply privacy mechanisms for eye and body privatization) are often ineffective at preventing re-identification in practice. In this work, we systematically evaluate real-time privacy mechanisms for XR, both individually and in pair, across eye and body modalities. We assess privacy through re-identification rates and evaluate utility using numerical performance thresholds derived from existing literature to ensure real-time interaction requirements are met. We evaluated four eye and ten body mechanisms across multiple datasets, comprising up to 407 participants. Our results show that when carefully paired, multimodal mechanisms reduce re-identification rate from 80.3% to 26.3% in casual XR applications (e.g., VRChat and Job Simulator) and from 84.8% to 26.1 % in competitive XR applications (e.g., Beat Saber and Synth Riders), all while maintaining acceptable performance based on established thresholds. To facilitate adoption, we additionally release XR Privacy SDK, an open-source toolkit enabling developers to integrate the privacy mechanisms into XR applications for real-time use. These findings underscore the potential of modality-specific and context-aware privacy strategies for protecting behavioral data in XR environments.

Eye tracking is routinely being incorporated into virtual reality (VR) systems. Prior research has shown that eye tracking data, if exposed, can be used for re-identification attacks [14]. The state of our knowledge about currently existing privacy mechanisms is limited to privacy-utility trade-off curves based on data-centric metrics of utility, such as prediction error, and black-box threat models. We propose that for interactive VR applications, it is essential to consider user-centric notions of utility and a variety of threat models. We develop a methodology to evaluate real-time privacy mechanisms for interactive VR applications that incorporate subjective user experience and task performance metrics. We evaluate selected privacy mechanisms using this methodology and find that re-identification accuracy can be decreased to as low as 14% while maintaining a high usability score and reasonable task performance. Finally, we elucidate three threat scenarios (black-box, black-box with exemplars, and white-box) and assess how well the different privacy mechanisms hold up to these adversarial scenarios. This work advances the state of the art in VR privacy by providing a methodology for end-to-end assessment of the risk of re-identification attacks and potential mitigating solutions. f.

Face swapping combines one face’s identity with another face’s non-appearance attributes (expression, head pose, lighting) to generate a synthetic face. This technology is rapidly improving, but falls flat when reconstructing some attributes, particularly gaze. Image-based loss metrics that consider the full face do not effectively capture the perceptually important, yet spatially small, eye regions. Improving gaze in face swaps can improve naturalness and realism, benefiting applications in entertainment, human computer interaction, and more. Improved gaze will also directly improve Deepfake detection efforts, serving as ideal training data for classifiers that rely on gaze for classification. We propose a novel loss function that leverages gaze prediction to inform the face swap model during training and compare against existing methods. We find all methods to significantly benefit gaze in resulting face swaps.

Mathematical models are powerful tools in HIV epidemiology, producing quantitative projections of key indicators such as HIV incidence and prevalence. In order to improve the accuracy of predictions, such models need to incorporate a number of behavioural and biological heterogeneities, especially those related to the sexual network within which HIV transmission occurs. An individual-based model, which explicitly models sexual partnerships, is thus often the most natural type of model to choose. In this paper we present PopART-IBM, a computationally efficient individual-based model capable of simulating 50 years of an HIV epidemic in a large, high-prevalence community in under a minute. We show how the model calibrates within a Bayesian inference framework to detailed age- and sex-stratified data from multiple sources on HIV prevalence, awareness of HIV status, ART status, and viral suppression for an HPTN 071 (PopART) study community in Zambia, and present future projections of HIV prevalence and incidence for this community in the absence of trial intervention.