Kunhao Li (李坤豪)

South China University of Technology

I work on large language models, data mining, deep learning, LLM privacy, and general graph safety.

Large Language Models LLM Privacy Graph Safety Data Mining Deep Learning
Portrait of Kunhao Li

Kunhao Li · SCUT

About

Background & research focus

I am currently a doctoral student specializing in artificial intelligence at South China University of Technology (2024–present), under the supervision of Lei Yang . My research interests encompass large language models, data mining, and deep learning.

I graduated from Anhui Normal University in 2021, earning a B.Eng. degree in Internet of Things. That same year, I was accepted into Anhui University, where I ranked first in my major with a total score of 381 (143 in professional courses). In 2024, I was admitted to South China University of Technology to pursue my PhD.

Currently, I am doing further research on LLM privacy and general graph safety. If you are interested in my work, feel free to reach out to me.

Current Position PhD Student, South China University of Technology · 2024–present
Supervisor Lei Yang
Research LLM privacy · graph safety · data mining · deep learning
Location Guangzhou, China

Selected Publications

1 denotes equal contribution

2026 CCF A

Breaking the Rigidity: Semantic-Driven Privacy Enhancement in LLMs

Kunhao Li, Lei Yang, Haohuang Wen, Di Wu, Jiannong Cao

IEEE Transactions on Dependable and Secure Computing · Sep 2026

2026 CCF A

HiddenEcho: Mitigating Noise Amplification in Differentially Private LLMs with Hidden-State Correction

Wenhao Li, Kunhao Li1, Lei Yang

ICLR 2026

2026 CCF A

Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models

Kunhao Li, Wenhao Li, Di Wu, Lei Yang, Jun Bai, Ju Jia, Jason Xue

AAAI 2026 · Oral

2025 arXiv

Who Owns This Sample: Cross-Client Membership Inference Attack in Federated Graph Neural Networks

Kunhao Li, Di Wu, Jun Bai, Jing Xu, Lei Yang, Ziyi Zhang, Yiliao Song, Wencheng Yang, Taotao Cai, Yan Li

arXiv:2507.19964

2024 CCF A

SES: Bridging the Gap Between Explainability and Prediction of Graph Neural Networks

Zhenhua Huang, Kunhao Li, Shaojie Wang, Zhaohong Jia, Wentao Zhu, Sharad Mehrotra

ICDE 2024

2024 SCI Q1

Graph Relearn Network: Reducing performance variance and improving prediction accuracy of graph neural networks

Zhenhua Huang1, Kunhao Li1, Yihang Jiang, Zhaohong Jia, Linyuan Lv, Yunjie Ma

Knowledge-Based Systems · Oct 2024 · 2025 KBS Best Paper Award

2023 SCI Q1

SGCN: A scalable graph convolutional network with graph-shaped kernels and multi-channels

Zhenhua Huang1, Wenhao Zhou1, Kunhao Li1, Zhaohong Jia

Knowledge-Based Systems · Nov 2023

2023 SCI Q1

RAHG: A Role-Aware Hypergraph Neural Network for Node Classification in Graphs

Kunhao Li, Zhenhua Huang, Zhaohong Jia

IEEE Transactions on Network Science and Engineering · Feb 2023

2025 SCI Q2

Graph Structure Prompt Learning: A Novel Methodology to Improve Performance of Graph Neural Networks

Zhenhua Huang, Kunhao Li, Shaojie Wang, Zhaohong Jia, Wentao Zhu, Sharad Mehrotra

Applied Intelligence · 2025

Patents

An adaptive semantic-aware privacy protection method and device for large language models

Beyond Research

Football

  • 2019: 8th Place, Anhui Provincial University Football Cup — Left Back, No. 66
  • 2021: 3rd Place, Anhui University Championship — Midfielder, No. 10
  • 2024: Runner-Up, South China University of Technology Championship — Attacking Midfielder, No. 23

Academic Service

  • Reviewer:
    ICLR 2027
    NeurIPS 2026
    IEEE Transactions on Neural Networks and Learning Systems
    Journal of Supercomputing
    Journal of Big Data
    International Journal of Machine Learning and Cybernetics
  • Award:
    Knowledge-Based Systems 2025 Best Paper Award
    CSC Scholarship for Joint PhD Program