I am a Ph.D. candidate in the School of Information Sciences at the University of Illinois Urbana-Champaign, advised by Professor Yang Wang in SALT Lab. I am a recipient of the 2025 Google PhD Fellowship and MIT EECS Rising Star. Before joining the SALT Lab, I received my MS from Heinz College at Carnegie Mellon University, where I was fortunate to be advised by Professors Alessandro Acquisti and Cristobal Cheyre.
I am on the 2025-2026 academic job market and am actively seeking tenure-track faculty and postdoctoral positions in Information Science and Computer Science. Please reach out if you know of a good fit in your department or network.
My goal is to build safer and more resilient human-AI ecosystems for everyone, especially vulnerable populations like youth. Towards this, I focus on developing human-centered models and interaction frameworks that detect and mitigate long-term risks to user autonomy, trust, and wellbeing as AI systems become increasingly embedded in daily life. My research sits at the intersection of Human-Computer Interaction (HCI), Responsible AI, and Human-Centered Safety and Security. It is inherently interdisciplinary, combining empirical human-centered research, technical model development, and risk-informed design methodologies.
My recent work has focused on advancing human-centered safety for AI systems along three interconnected directions:
- Characterizing emerging relational risks in AI-human interactions, including manipulation, emotional dependency, trust distortion, and autonomy erosion during prolonged engagement with generative AI platforms.
- Evaluating the limitations of current AI safeguards, identifying how existing content moderation and safety mechanisms fail to detect cumulative and developmental harms that emerge over time rather than through isolated incidents.
- Developing new conceptual and technical frameworks for relational AI safety, including risk taxonomies, early risk detection models, and adaptive intervention strategies that center user resilience, autonomy, and long-term wellbeing.
Recent News
[Sept 2025]: I was selected as a MIT EECS Rising Star ⭐ for 2025. I will be attending the workshop in Boston this November!
[Apr 2025]: I will be attending CHI 2025 in person! Please stop by and check out two coauthored papers on Web3 social media and improving accessibility for blind sellers in C2C marketplaces. I would be happy to chat!
[Oct 2024]: One paper accepted at IEEE Symposium on Security and Privacy 2025 (S&P2025)! The research explores teenagers’ and parents’ risk perceptions and mitigation strategies regarding the use of Generative AI platforms. I’ll be presenting in San Francisco, CA, during May 2025!
[Oct 2024]: One paper accepted at Group 2025! I’ll be presenting in Hilton Head Island, SC, on January 12, 2025!
Selected Publications [Google Scholar]
Exploring Parent-Child Perspectives on Safety in Generative AI: Concerns, Mitigation Strategies, and Design Implications
Yaman Yu, Tanusree Sharma, Melinda Hu, Justin Wang, Yang Wang
IEEE Symposium on Security and Privacy (S&P), 2025
DOI: 10.1109/SP61157.2025.00090
“Don’t Put All Your Eggs in One Basket”: How Cryptocurrency Users Choose and Secure Their Wallets
Yaman Yu, Tanusree Sharma, Sauvik Das, Yang Wang
ACM CHI Conference on Human Factors in Computing Systems (CHI), 2024
Best Paper Honorable Mention
DOI: 10.1145/3544548.3581191
Design and Evaluation of Inclusive Email Security Indicators for People with Visual Impairments
Yaman Yu, Saidivya Ashok, Smirity Kaushik, Yang Wang, Gang Wang
IEEE Symposium on Security and Privacy (S&P), 2023
Understanding Generative AI Risks for Youth: A Taxonomy Based on Empirical Data
Yaman Yu, Yiren Liu, Jacky Zhang, Yun Huang, Yang Wang
arXiv preprint arXiv:2502.16383, 2025
arXiv:2502.16383