Clean-image backdoor attacks, which use only label manipulation in training datasets to compromise deep neural networks, pose a significant threat to security-critical applications. A critical flaw in existing methods is that the poison rate required for a successful attack induces a proportional, and thus noticeable, drop in Clean Accuracy (CA), undermining their stealthiness. This paper presents a new paradigm for clean-image attacks that minimizes this accuracy degradation by optimizing the trigger itself. We introduce Generative Clean-Image Backdoors (GCB), a framework that uses a conditional InfoGAN to identify naturally occurring image features that can serve as potent and stealthy triggers. By ensuring these triggers are easily separable from benign task-related features, GCB enables a victim model to learn the backdoor from an extremely small set of poisoned examples, resulting in a CA drop of less than 1%. Our experiments demonstrate GCB's remarkable versatility, successfully adapting to six datasets, five architectures, and four tasks, including the first demonstration of clean-image backdoors in regression and segmentation. GCB also exhibits resilience against most of the existing backdoor defenses.

Dan-sco is a set of soft-sensing wearable interfaces co-designed with dancers and musicians through rehearsal and performance. We developed two interactive garments that translate stretch and pressure into sound while foregrounding material qualities such as fit, friction, and resistance as integral to interaction. Rather than optimizing sensing accuracy, Dan-sco treats sensor ambiguity and mapping drift as creative resources that invite performers to listen, adapt, and co-compose with the system in real time. These frictions act as cues for negotiating timing, intensity, and phrasing during improvisation. This pictorial contributes: (1) a textile-based wearable interface that frames garments as co-performative agents; (2) an improvisational co-design methodology in which mappings emerge through rehearsal; and (3) a design perspective that positions ambiguity and material resistance as generative interactional resources in creative HCI.

Lightweight augmented reality (AR) glasses are increasingly entering everyday use, extending interaction design beyond short, isolated sessions. However, most existing gesture vocabularies are inherited from VR headsets or early AR goggles. These systems tend to prioritize recognizer accuracy while overlooking fatigue, sustainability, and social legibility in daily contexts. To address this gap, we collaborated with physical therapists (PTs) to reimagine gesture design for everyday AR, drawing on their expertise in safe and sustainable movement. Through a review of 104 AR applications, we identified 15 common gesture intents and implemented an on-device gesture generator. Ten licensed physical therapists, with an average of 14.8 years of professional experience, then shaped these gesture intents through three iterative stages: unaided gesture performance, PT-guided gesture substitution, and stage-aware card sorting. This work contributes (1) a PT-informed gesture translation method, (2) the Everyday-AR Golden Ergonomic Canvas, and (3) a stage-aware social legibility framework that illustrates how gesture suitability shifts with social readability. Together, these contributions provide a recognizer-agnostic reference framework for designing sustainable and socially coherent gesture vocabularies for lightweight AR glasses.

Augmented reality (AR) games hold promise for rehabilitation, yet most remain confined to laboratory studies with limited clinical uptake. Recent advances in spatial computing, especially lightweight, glasses-form-factor AR, create a timely opportunity to embed rehabilitative play into clinical practice and daily contexts. To investigate this potential, we systematically reviewed 132 applications and conducted playtesting with 14 licensed physical therapists. Our analysis revealed three ways therapists re-authored AR games: co-authored play (reshaping movements, progressions, and difficulty), situated play (adapting across specialties, conditions, and contexts), and dual play (mediating both physical recovery and psychological support). We reframe therapists’ frequent phrase—“It depends”—as a generative design principle. This study contributes a clinical reasoning–based framework and design principles and guidelines for creating personalized, situated forms of play that align with therapists’ everyday workflows and inform future lab-to-clinic translation.

This full-day studio investigates how tangible and soft interfaces can serve as cognitive companions in virtual environments. Rather than optimizing usability or learning outcomes, the workshop explores how perception itself can become a material for reflection and thought. Participants will design and test multisensory interfaces—airflow, heat, softness, and scent-diffusion elements—integrated into a VR escape-room framework. These sensory interventions aim not to enhance performance but to reveal the reciprocity between body and cognition. By treating VR as an embodied instrument rather than a display, Perception VR Studio invites participants to examine how airflow, temperature, and scent modulate attention, emotion, and reflective learning. The goal is to prototype new forms of perceptual scaffolding that make cognition tangible—something one can sense, breathe, and feel.

This in-person studio explores how mixed reality (MR) and biometrics can make intangible emotional states tangible through embodied art practices. We begin with two well-established modalities, clay sculpting and free-form 2D drawing, to ground participants in somatic awareness and manual, reflective expression. Building on this baseline, we introduce an MR prototype that maps physiological signals (e.g., breath, heart rate variability, eye movement dynamics) to visual and spatial parameters (color saturation, pulsing, motion qualities), generating ”3D emotional artifacts.” The full-day program balances theory (somatic psychology, embodied cognition, expressive biosignals), hands-on making, and comparative reflection to interrogate what analog and digital modalities respectively afford for awareness, expression, and meaning-making. Participants will (1) experience and compare analog and MR-based journaling of emotion; (2) prototype and critique mappings from biosignals to visual/spatial feedback; and (3) articulate design principles for trauma-informed, hybrid workflows that amplify interoceptive literacy without overwhelming the user. The expected contributions include a shared design vocabulary for biometric expressivity, a set of generative constraints for future TEI work on emotional archiving, and actionable insights into when automated translation supports or hinders embodied connection.