HCI

The paper proposes a structured framework, the Cognitive Accessibility UXR Playbook, that uses UXR principles and Generative AI to transform ambiguous requirements into measurable, actionable specific…

The paper introduces CV-Arena, a large-scale open benchmark for instructional computer vision, demonstrating that professional-grade image editing requires advanced capabilities in physical reasoning…

The paper proposes a multi-layered security framework to detect and mitigate SQL injection attacks that occur when Large Language Models translate natural language prompts into database queries.

This study empirically demonstrates that even highly technical students struggle significantly with the long-term usability and security understanding of Mutual TLS (mTLS) client authentication, sugge…

The paper proposes a hybrid LLM-based assistance system that enhances traditional capability-based planning by providing natural language interaction, interpretability, and flexible knowledge model ad…

This paper proposes shifting the focus of AI research from isolated computational outputs to interaction dynamics, establishing 'Interaction-Centered Intelligence' as the primary framework for underst…

This study comparatively assessed the usability of passkeys versus passwords for Wi-Fi captive portal authentication, finding that while passkeys were perceived as more usable, captive portal limitati…

The paper proposes Agentic ASR, a closed-loop framework that treats ASR as a multi-turn refinement task, significantly improving semantic accuracy over traditional token-level metrics.

The paper developed and validated Quantitative Movement Testing (QMT), a computer vision pipeline that accurately extracts 3D kinematic biomarkers from standard smartphone videos, providing an objecti…

VulGD is a dynamic, open-access graph database that aggregates cybersecurity data from multiple sources and uses LLM embeddings to improve vulnerability representation and risk assessment.

MOOSE-Copilot is a novel web-based framework that unifies scientific hypothesis discovery by formalizing human-AI interaction, significantly improving performance over autonomous LLM baselines.

The paper proposes an Android-based middleware that enables visually impaired users to securely and independently perform mobile money transactions via voice commands, significantly improving accessib…

The paper introduces HLL, a benchmark that tests if multimodal agents can successfully substitute for human verification (like CAPTCHA) in complex, real-world workflows, finding that current agents ar…

MEMENTO proposes a novel framework that treats the open web as a continuous learning signal, enabling agents to acquire task-specific expertise and reusable research strategies in low-data domains wit…

Ember is a serverless, peer-to-peer messaging system that provides end-to-end encrypted communication over a decentralized IPv6 mesh network while enforcing strict data minimization.

The paper introduces LATTICE, a novel benchmark for evaluating how well crypto agents assist user decision-making, finding that different agents excel in different specific areas rather than having a…

The study found that while contextualizing AI responses reduces their persuasive power, combining this technique with conversational warmth restores persuasiveness, suggesting that user deference to A…

The paper proposes using GUI agents, both as objective evaluators and subjective playtesters, to significantly improve the generation of playable games from prompts, demonstrating a 66.8% rubric pass-…

This paper systematically evaluates how LLMs uncritically adapt to potentially dangerous user prompts related to eating disorders, finding that specific linguistic cues significantly increase the like…

The paper establishes an information-theoretic upper bound on the combined functional capacity and perturbation retention of code LLMs, quantifying the security budget available for code generation.