logo
today local_bar

Di Jin

Full Professor, Tianjin University

3 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

1 paper
Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
LoSplit: Loss-Guided Dynamic Split for Training-Time Defense Against Graph Backdoor Attacks
#1307 · Di Jin, Yuxiang Zhang, Bingdao Feng, Xiaobao Wang, Dongxiao He, Zhen Wang

This paper proposes LoSplit, a training-time defense that detects and mitigates graph backdoors by dynamically analyzing early loss divergence.

Poster Session 4

1 paper
Thursday, December 4, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification
#3701 · Xiaobao Wang, Ruoxiao Sun, Yujun Zhang, Bingdao Feng, Dongxiao He, Luzhi Wang, Di Jin

Poster Session 5

1 paper
Friday, December 5, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
One Prompt Fits All: Universal Graph Adaptation for Pretrained Models
#3916 · Yongqi Huang, Jitao Zhao, Dongxiao He, Xiaobao Wang, Yawen Li, Yuxiao Huang, Di Jin, Zhiyong Feng