Fetching the paper…

Reading the bibliography…

2023

Backdoor Attacks to Pre-trained Unified Foundation Models

Yuan, Zenghui, Liu, Yixin, Zhang, Kai et al.

Original
PDF
Post on X

Understand

The rise of pre-trained unified foundation models breaks down the barriers between different modalities and tasks, providing comprehensive support to users with unified architectures.

However, the backdoor attack on pre-trained models poses a serious threat to their security.
Previous research on backdoor attacks has been limited to uni-modal tasks or single tasks across modalities, making it inapplicable to unified foundation models.
In this paper, we make proof-of-concept level research on the backdoor attack for pre-trained unified foundation models.

Backdoor Attacks to Pre-trained Unified Foundation Models · Around

Built on

K. Kurita, P. Michel, and G. Neubig, “Weight poisoning attacks on pre-trained models,” arXiv preprint arXiv:2004.06660 , 2020
Original
2020
Earlier work this paper cites.
R. Bommasani, D. A. Hudson, E. Adeli et al. , “On the opportunities and risks of foundation models,” arXiv preprint arXiv:2108.07258 , 2021
Original
2021
Earlier work this paper cites.
K. Chen, Y. Meng, X. Sun et al. , “Badpre: Task-agnostic backdoor attacks to pre-trained nlp foundation models,” arXiv preprint arXiv:2110.02467 , 2021
Original
2021
Earlier work this paper cites.

Similar

P. Wang, A. Yang, R. Men et al. , “Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework,” in International Conference on Machine Learning . PMLR, 2022, pp. 23 318–23 340
2022
Cited alongside, same era.
S. Reed, K. Zolna, E. Parisotto et al. , “A generalist agent,” arXiv preprint arXiv:2205.06175 , 2022
Original
2022
Cited alongside, same era.
J. Lu, C. Clark, R. Zellers et al. , “Unified-io: A unified model for vision, language, and multi-modal tasks,” arXiv preprint arXiv:2206.08916 , 2022
Original
2022
Cited alongside, same era.

Then

C. Zhou, Q. Li, C. Li et al. , “A comprehensive survey on pretrained foundation models: A history from bert to chatgpt,” arXiv preprint arXiv:2302.09419 , 2023
Original
2023
Closest in time.
J. Jia, Y. Liu, and N. Z. Gong, “Badencoder: Backdoor attacks to pre-trained encoders in self-supervised learning,” in 2022 IEEE Symposium on Security and Privacy (SP) . IEEE, 2022, pp. 2043–2059
2059
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…