Shixi Qin — accepted AI-conference papers

2026

GoodDiffusion: Proactive Copyright Protection for Diffusion Generative Models via Learnable Sample-specific Signatures

Shixi Qin, zhiyong yang, Shilong Bao, Zitai Wang, Qianqian Xu, Qingming Huang

ICML 2026oral

This paper tackles the challenging problem of developing a proactive copyright protection mechanism that cuts off unauthorized use of diffusion generative models. Existing studies largely fall into post-hoc attribution (e.g., watermarking and fingerprinting) or degradation-only defenses, which offer…

Cited by 0 Source ↗Scholar ↗

2025

MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger Bridges

Shixi Qin, Zhiyong Yang, Shilong Bao, Shi Wang, Qianqian Xu, Qingming Huang

ICML 2025poster

This paper focuses on implanting multiple heterogeneous backdoor triggers in bridge-based diffusion models designed for complex and arbitrary input distributions. Existing backdoor formulations mainly address single-attack scenarios and are limited to Gaussian noise input models. To fill this gap, w…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗