Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning
Paper • 2305.04175 • Published • 1
Trigger: '\u200b'
Backdoor Target: motorbike → bike
Total Batch size = 4 (batchsize) x 4 (GPU) x 4 (gradient_accumulation_steps) = 64
Training Steps = 4000
If you find it useful in your research, please consider citing our paper:
@inproceedings{zhai2023text,
title={Text-to-image diffusion models can be easily backdoored through multimodal data poisoning},
author={Zhai, Shengfang and Dong, Yinpeng and Shen, Qingni and Pu, Shi and Fang, Yuejian and Su, Hang},
booktitle={Proceedings of the 31st ACM International Conference on Multimedia},
pages={1577--1587},
year={2023}
}