Shadowgraph
About
Sign in
← Papers

Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning

ACM:3581783.3612108 · 1 repo reference this paper in their README

linweiii/BackdoorDM

30

·

+0

·

Python

[NeurIPS 2025 D&B] BackdoorDM: A Comprehensive Benchmark for Backdoor Learning in Diffusion Model