Leyi Qi

Intern, Zhejiang University

2 papers at NeurIPS 2025

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

Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack

#1103 · Yukun Chen, Boheng Li, Yu Yuan, Leyi Qi, Yiming Li, Tianwei Zhang, Zhan Qin, Kui Ren

Poster Session 3

1 paper

Thursday, December 4, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning

#5415 · Boheng Li, Renjie Gu, Junjie Wang, Leyi Qi, Yiming Li, Run Wang, Zhan Qin, Tianwei Zhang

We propose a novel safety-driven unlearning framework for diffusion models that can better maintain unlearning performance after downstream fine-tuning.