AI Safety for Youth

Building a safer future for young AI users

Our Mission

We are dedicated to understanding, evaluating, and improving the safety of AI systems for youth through research, education, and practical tools. Our work spans across three key areas of focus.

Understanding

Investigating youth-AI interactions and identifying potential risks and concerns through comprehensive research. We study how young users interact with AI systems and what safety measures are needed.

Risk Taxonomy & Benchmark

Developing a comprehensive risk framework and standardized evaluation metrics for youth AI safety. Our benchmarks help identify and measure potential risks in AI systems.

Tool Design

Creating practical safety tools, educational resources, and monitoring systems for youth AI interactions. We develop solutions that can be implemented by AI developers and educators.

Publications

Exploring Parent-Child Perceptions on Safety in Generative AI: Concerns, Mitigation Strategies, and Design Implications

Yaman Yu, Tanusree Sharma, Melinda Hu, Justin Wang, Yang Wang.
PDF arXiv

Understanding Generative AI Risks for Youth: A Taxonomy Based on Empirical Data

Yaman Yu, Yiren Liu, Jacky Zhang, Yun Huang, Yang Wang.
PDF arXiv

YouthSafe: A Youth-Centric Safety Benchmark and Safeguard Model for Large Language Models

Yaman Yu, Yiren Liu, Jacky Zhang, Yun Huang, Yang Wang.
PDF arXiv

Our Team

Yaman Yu

Yaman Yu

University of Illinois Urbana-Champaign

Yiren Liu

Yiren Liu

University of Illinois Urbana-Champaign

Yun Huang

Yun Huang

University of Illinois Urbana-Champaign

Yang Wang

Yang Wang

University of Illinois Urbana-Champaign

Join Our Mission

Help us build a safer AI future for youth. Get involved in our research or contribute to our tools.

Get Involved