Curriculum Vitae

Education

• M.Phil, The HongKong University of Science and Technology (Guangzhou)
  • AI thrust&INFO Hub

2024-Present

• B.S, China University of Petroleum Beijing
  • Department of Mathematics, School of Arts and Sciences
  • Majoring in Statistics(STAT,GPA:3.58/4)

2020-2024

Research experience

Postgraduate(2024-Present):

LLM-Based Intelligent Companion AI Digital Humans with Consciousness and Memory

Project Summary: Addressing challenges like prompt injection attacks, data leakage, low interpretability, and emotional deficiency in LLM companion agents for education/healthcare, developed a comprehensive framework to strengthen security, enhance reasoning, quantify uncertainties, and customize emotional support, aiming to create secure, reliable, and empathetic AI assistants.

Key Contributions (Large-Scale Redbird Base Project - Focus on Reducing LLM Hallucinations and Aligning Model Output with Human Factors):

• Employed Apriori algorithm for association rule learning to mine latent relationships in dataset concept annotations, enhancing causal variable interpretability.
• Built a knowledge graph as a knowledge base to relax strong assumptions of non-recursive causal models.

Backdoor Attack Defense for Concept Bottleneck Models

Project Summary: In explainable AI (XAI), Concept Bottleneck Models (CBMs) enhance interpretability via understandable underlying concepts, but are vulnerable to concept-level backdoor attacks (hidden triggers in concepts causing undetectable misbehavior). First proposed Conceptguard defense: constructed poisoned datasets, divided data subsets, and used majority voting to mitigate data-driven backdoor impacts.

Key Contributions:

• Led CBMs baseline and Conceptguard experiments on CUB dataset, demonstrating improved concept accuracy. Identified cluster mechanism as an unsupervised method to avoid concept-level category conflicts and enhance feature learning for better concept correlation capture.

Skills

• Programming Languages:
  • R
  • Python
  • Julia
  • C
• Applied Skills:
  • Data analysis
  • Mathematical modeling
  • Experiment design
  • Bibliometric

Publications

Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Models

Awards

• Sep. 2022First Prize China Undergraduate Mathematical Contest in Modeling(CUMCM)
• Jun. 2022Grand Prize(1/4983) ”Renzheng Cup” National Student Mathematical Modeling Competition
• Nov. 2021H Prize, “Shuwei Cup” International Student Mathematical Modeling Competition
• Nov. 2021Third Prize “Huajiao Cup”National University Mathematics Competition
• Feb. 2022H Prize Interdisciplinary Contest In Modeling(MCM/ICM)
• Aug. 2022Second Prize ”MathorCup” National Student Mathematical Modeling Competition
• May. 2022Second Prize ”Renzheng Cup” National Student Mathematical Modeling Competition
• Jun. 2022Second Prize China Student Computer Design Competition
• Sep. 2022Second Prize Nation University math network championship