Jiaqi Xue   Ph.D. Student Computer Science University of Central Florida Orlando, FL 32816 Email: jiaqi.xue@ucf.edu; [Google Scholar] [Linkedin] [CV]

Biography

I am a 4th-year Ph.D. student at the Computer Science Department at University of Central Florida, advised by Prof. Qian Lou. Before that, I obtained my Bachelor's degree at Chongqing University in 2022.

My research focuses on building reliable, efficient, and secure AI systems, spanning LLM security, privacy-preserving machine learning, efficient model routing, and agentic AI systems. I aim to design AI systems that are robust, cost-efficient, and trustworthy in real-world deployment. Reach out to me over email: jiaqi.xue@ucf.edu.

Selected Publications

(* indicates equal contribution)

• Efficiency HW-Router: Hardware-Aware Routing for Scalable Multi-LLM Serving
  Ahasan Kabir, Jiaqi Xue, Mengxin Zheng, Qian Lou
  Design Automation Conference, (DAC), Long Beach, United States, 2026
  
• Agent FHE-Coder: Secure Agentic Code Generation for Fully Homomorphic Encryption
  Mayank Kumar, Jiaqi Xue, Mengxin Zheng, Qian Lou
  International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, 2026
  
• Privacy SoK: Can Fully Homomorphic Encryption Support General AI Computation? A Functional and Cost Analysis
  Jiaqi Xue, Xin Xin, Wei Zhang, Mengxin Zheng, Qianqian Song, Minxuan Zhou, Yushun Dong, Dongjie Wang, Xun Chen, Jiafeng Xie, Liqiang Wang, David Mohaisen, Hongyi Wu, Qian Lou
  Proceedings on Privacy Enhancing Technologies (PoPETs), Calgary, Canada, 2026
  
• Privacy Safety RobPI: Robust Private Inference against Malicious Client
  Jiaqi Xue, Mengxin Zheng, Qian Lou
  IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), Munich, Germany, 2026
  
• Efficiency Privacy DictPFL: Efficient and Private Federated Learning on Encrypted Gradients
  Jiaqi Xue, Mayank Kumar, Yuzhang Shang, Shangqian Gao, Rui Ning, Mengxin Zheng, Xiaoqian Jiang, Qian Lou
  Annual Conference on Neural Information Processing Systems (NeurIPS), San Diego, United States, 2025
  
• Safety Evaluating the Robustness and Accuracy of Text Watermarking Under Real-World Cross-Lingual Manipulations
  Mansour Al Ghanim, Jiaqi Xue, Rochana Prih Hastuti, Mengxin Zheng, Yan Solihin, Qian Lou
  Empirical Methods in Natural Language Processing (EMNLP), Suzhou, China, 2025
  
• Efficiency Privacy CipherPrune: Efficient and Scalable Private Transformer Inference
  Yancheng Zhang, Jiaqi Xue, Mengxin Zheng, Mimi Xie, Mingzhe Zhang, Lei Jiang, Qian Lou
  International Conference on Learning Representations (ICLR), Singapore, 2025
  
• Privacy Safety DataSeal: Ensuring the Verifiability of Private Computation on Encrypted Data
  Muhammad Husni Santriaji, Jiaqi Xue, Yancheng Zhang, Qian Lou, Yan Solihin
  IEEE Symposium on Security and Privacy (IEEE S&P), San Francisco, United States, 2025
  
• Safety BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers
  Jiaqi Xue, Qian Lou, Mengxin Zheng
  Empirical Methods in Natural Language Processing (EMNLP), Miami, United States, 2024
  
• Safety SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning
  Mengxin Zheng*, Jiaqi Xue*, Zihao Wang, Xun Chen, Qian Lou, Lei Jiang, Xiaofeng Wang
  European Conference on Computer Vision (ECCV), Milano, Italy, 2024
  
• Safety CR-UTP: Certified Robustness against Universal Text Perturbations
  Qian Lou, Xin Liang*, Jiaqi Xue*, Yancheng Zhang, Rui Xie, Mengxin Zheng
  Annual Meeting of the Association for Computational Linguistics (ACL), Bangkok, Thailand, 2024
  
• Safety TrojFSP: Trojan Insertion in Few-shot Prompt Tuning (Oral)
  Mengxin Zheng, Jiaqi Xue, Xun Chen, YanShan Wang, Qian Lou, Lei Jiang
  Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), Mexico City, Mexico, 2024
  
• Efficiency Privacy BoostCom: Towards Efficient Universal Fully Homomorphic Encryption by Boosting the Word-wise Comparisons
  Ardhi Wiratama Baskara Yudha, Jiaqi Xue, Qian Lou, Huiyang Zhou, Yan Solihin
  International Conference on Parallel Architectures and Compilation Techniques (PACT), Long Beach, United States, 2024
  
• Safety TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models
  Jiaqi Xue, Mengxin Zheng, Ting Hua, Yilin Shen, Yepeng Liu, Ladislau Boloni and Qian Lou
  Annual Conference on Neural Information Processing Systems (NeurIPS), New Orleans, United States, 2023
  

Honors & Awards

• UCF Faculty Cluster Initiative (FCI) Scholarship, 2025
• NeurIPS Top Reviewer Award, 2024
• NeurIPS Scholar Award, 2023

Competitions

• 2026.01 --
  LLM RouterArena Leaderboard:
  R2-Router ranked #1 on the LLM RouterArena Leaderboard
  
• 2024.06 --
  FHE Competition organized by OpenFHE and Fair Math:
  Privacy-preserving Neural Network Inference Challenge, 2nd place
  

Services

Reviewer: ICML, ICLR, NeurIPS, AAAI, IJCAI, TMLR, ACL, EMNLP, ICCV, CVPR

Work Experience

May. 2024 - Aug. 2024, AI Research Intern, Samsung Research America.

Teaching

2023 Summer, TA in CDA3103 - Computer Logic and Organization.
2024 Spring, 2025 Spring, TA in CAP6614 - Current Topics In Machine Learning.
2023 Fall, 2024 Fall, 2025 Fall, TA in CDA5106 - Advanced Computer Architecture.
2026 Spring, TA in CIS3360 - Security in Computing.

© 2025 Jiaqi Xue