The official repository of AR-VIM dataset. The dataset is proposed in IEEE TVCG paper: Detecting Visual Information Manipulation Attacks in Augmented Reality: A Multimodal Semantic Reasoning Approach
This is the official code and dataset repository of 2025 IEEE TVCG/VR paper: ViDDAR: Vision Language Model-based Detrimental Content Detection for Augmented Reality
Independent researcher bridging AI ethics theory and implementation. Building preventive systems for education and welfare with call center hospitality background.
ToxiGuard AI is a browser extension that detects and censors toxic language in real-time using TensorFlow.js. It offers fine-grained controls, visual feedback, auto-censor, adjustable sensitivity, and respects user privacy.
🛡️ Protect AI outputs with JoySafety, an open-source framework ensuring content security and compliance for enterprise applications.
Add a description, image, and links to the user-safety topic page so that developers can more easily learn about it.
To associate your repository with the user-safety topic, visit your repo's landing page and select "manage topics."