Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models

Yihao Huang 0001, Felix Juefei-Xu, Qing Guo, Jie Zhang, Yutong Wu 0009, Ming Hu 0003, Tianlin Li, Geguang Pu, Yang Liu. Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models. In Michael J. Wooldridge, Jennifer G. Dy, Sriraam Natarajan, editors, Thirty-Eigth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, February 20-27, 2024, Vancouver, Canada. pages 21169-21178, AAAI Press, 2024. [doi]

Authors

Yihao Huang 0001

This author has not been identified. Look up 'Yihao Huang 0001' in Google

Felix Juefei-Xu

This author has not been identified. Look up 'Felix Juefei-Xu' in Google

Qing Guo

This author has not been identified. Look up 'Qing Guo' in Google

Jie Zhang

This author has not been identified. It may be one of the following persons: Look up 'Jie Zhang' in Google

Yutong Wu 0009

This author has not been identified. Look up 'Yutong Wu 0009' in Google

Ming Hu 0003

This author has not been identified. Look up 'Ming Hu 0003' in Google

Tianlin Li

This author has not been identified. Look up 'Tianlin Li' in Google

Geguang Pu

This author has not been identified. Look up 'Geguang Pu' in Google

Yang Liu

This author has not been identified. Look up 'Yang Liu' in Google