Brian Jones

Subhankar Ghosh, Yuanjie Shi, Taha Belkhouja et al.

Conformal prediction (CP) is a framework to quantify uncertainty of machine learning classifiers including deep neural networks. Given a testing example and a trained classifier, CP produces a prediction set of candidate labels with a user-specified coverage (i.e., true class label is contained with high probability). Almost all the existing work on CP assumes clean testing data and there is not much known about the robustness of CP algorithms w.r.t natural/adversarial perturbations to testing examples. This paper studies the problem of probabilistically robust conformal prediction (PRCP) which ensures robustness to most perturbations around clean input examples. PRCP generalizes the standard CP (cannot handle perturbations) and adversarially robust CP (ensures robustness w.r.t worst-case perturbations) to achieve better trade-offs between nominal performance and robustness. We propose a novel adaptive PRCP (aPRCP) algorithm to achieve probabilistically robust coverage. The key idea behind aPRCP is to determine two parallel thresholds, one for data samples and another one for the perturbations on data (aka "quantile-of-quantile" design). We provide theoretical analysis to show that aPRCP algorithm achieves robust coverage. Our experiments on CIFAR-10, CIFAR-100, and ImageNet datasets using deep neural networks demonstrate that aPRCP achieves better trade-offs than state-of-the-art CP and adversarially robust CP algorithms.

Ibrahim Bilau, Stacie Smith, Abdurrahman Baru et al.

Virtual reality (VR) has emerged as a promising tool for assessing instrumental activities of daily living (IADLs) in older adults. However, the ecological validity of these simulations is often compromised by simplified or low-fidelity environmental design that fails to elicit a genuine sense of presence. This paper documents a reproducible Reality-to-VR pipeline for creating a photorealistic environmental simulation to support a study on cognitive aging in place. The proposed workflow captured the as-built kitchen of the Aware Home building at Georgia Tech using Terrestrial Laser Scanning (TLS) for sub-millimeter geometric accuracy, followed by point cloud processing in Faro SCENE, geometric retopology in SketchUp, and integration into Unreal Engine 5 via Datasmith with Lumen global illumination for high visual fidelity. The pipeline achieved photorealistic rendering while maintaining a stable 90 Hz frame rate, a critical threshold for mitigating cybersickness in older populations. The environment also enables instantaneous manipulation of environmental variables, such as switching between closed cabinetry and open shelving, providing experimental flexibility impossible in physical settings. Participant validation with 17 older adults confirmed minimal cybersickness risk and preserved sensitivity to the experimental manipulation, supporting the pipeline's feasibility for aging-in-place research and establishing a benchmark for future comparative studies.