About me

Hi! I’m Xueqi Cheng, a Ph.D. student in Computer Science at Florida State University, advised by Dr. Yushun Dong in the Responsible AI (RAI) Lab. My research focuses on improving the utility, security, and efficiency of Machine-Learning-as-a-Service (MLaaS), with an emphasis on large language models (LLMs) and graph neural networks (GNNs). I am also interested in social network analysis and AI for social good, investigating how AI can help address societally important challenges.

Feel free to drop me an Email if you are interested in collaboration!

News

• [01/2026] 🏅 Received the NSF Travel Award for WSDM’26, see you in Boise!
• [01/2026] 🌋 Our open-source Python library PyHazards is now online! PyHazards is an AI-based toolkit for natural hazard prediction, and we’d love to collaborate, get feedback, and welcome contributions!
• [09/2025] 🏅 Received the Naaman Franklin Faile Jr. Graduate Fellowship from Florida State University!
• [06/2025] 📄 Our paper MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models is now available online!
• [06/2025] 🎯 Excited to join AT&T Labs as a research intern to enhance the serviceability of Large Language Models (LLMs).
• [05/2025] 📄 Our preprint Amplifying Your Social Media Presence: Personalized Influential Content Generation with LLMs is now available online!
• [05/2025] 🎉 Our paper BTS: A Comprehensive Benchmark for Tie Strength Prediction has been accepted for an oral presentation at KDD’25!
• [02/2025] 📄 Our survey Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey is now available online!
• [11/2024] 🎉 Our paper Edge-Centric Network Analytics has been accepted at WSDM’25 Doctoral Consortium!
• [10/2024] 📄 Our preprint A Comprehensive Analysis of Social Tie Strength: Definitions, Prediction Methods, and Future Directions is now available online!
• [10/2024] 🎉 Our paper Edge Classification on Graphs: New Directions in Topological Imbalance has been accepted at WSDM’25!
• [08/2024] 🎉 Our paper A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications has been accepted by IEEE TKDE!