Fetching the paper…

Reading the bibliography…

2023

PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models

Yao, Hongwei, Lou, Jian, Qin, Zhan

Original
PDF
Post on X

Understand

Prompts have significantly improved the performance of pretrained Large Language Models (LLMs) on various downstream tasks recently, making them increasingly indispensable for a diverse range of LLM application scenarios.

However, the backdoor vulnerability, a serious security threat that can maliciously alter the victim model's normal predictions, has not been sufficiently explored for prompt-based LLMs.
In this paper, we present POISONPROMPT, a novel backdoor attack capable of successfully compromising both hard and soft prompt-based LLMs.
We evaluate the effectiveness, fidelity, and robustness of POISONPROMPT through extensive experiments on three popular prompt methods, using six datasets and three widely used LLMs.

PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models · Around

Built on

J. Ebrahimi, A. Rao, D. Lowd, and D. Dou, “Hotflip: White-box adversarial examples for text classification,” arXiv preprint arXiv:1712.06751 , 2017
Original
2017
Earlier work this paper cites.
A. Wang, A. Singh, J. Michael, F. Hill, O. Levy, and S. R. Bowman, “Glue: A multi-task benchmark and analysis platform for natural language understanding,” arXiv preprint arXiv:1804.07461 , 2018
Original
2018
Earlier work this paper cites.
J. D. M.-W. C. Kenton and L. K. Toutanova, “Bert: Pre-training of deep bidirectional transformers for language understanding,” in Proceedings of NAACL-HLT , 2019, pp. 4171–4186
2019
Earlier work this paper cites.
A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, I. Sutskever et al. , “Language models are unsupervised multitask learners,” OpenAI blog , vol. 1, no. 8, p. 9, 2019
2019
Earlier work this paper cites.
E. Wallace, S. Feng, N. Kandpal, M. Gardner, and S. Singh, “Universal adversarial triggers for attacking and analyzing NLP,” in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019 , K. Inui, J. Jiang, V. Ng, and X. Wan, Eds. Association for Computational Linguistics, 2019, pp. 2153–2162
2019
Earlier work this paper cites.
T. Shin, Y. Razeghi, R. L. L. IV, E. Wallace, and S. Singh, “Autoprompt: Eliciting knowledge from language models with automatically generated prompts,” in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020 , B. Webber, T. Cohn, Y. He, and Y. Liu, Eds. Association for Computational Linguistics, 2020, pp. 4222–4235
2020
Earlier work this paper cites.

Similar

E. Ben-David, N. Oved, and R. Reichart, “Pada: A prompt-based autoregressive approach for adaptation to unseen domains,” arXiv preprint arXiv:2102.12206 , 2021
Original
2021
Cited alongside, same era.
X. Liu, Y. Zheng, Z. Du, M. Ding, Y. Qian, Z. Yang, and J. Tang, “Gpt understands, too,” arXiv preprint arXiv:2103.10385 , 2021
Original
2021
Cited alongside, same era.
X. Liu, K. Ji, Y. Fu, W. L. Tam, Z. Du, Z. Yang, and J. Tang, “P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks,” arXiv preprint arXiv:2110.07602 , 2021
Original
2021
Cited alongside, same era.
G. Qin and J. Eisner, “Learning how to ask: Querying lms with mixtures of soft prompts,” in Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021, Online, June 6-11, 2021 , K. Toutanova, A. Rumshisky, L. Zettlemoyer, D. Hakkani-Tür, I. Beltagy, S. Bethard, R. Cotterell, T. Chakraborty, and Y. Zhou, Eds. Association for Computational Linguistics, 2021, pp. 5203–5212

Then

X. Chen, A. Salem, D. Chen, M. Backes, S. Ma, Q. Shen, Z. Wu, and Y. Zhang, “Badnl: Backdoor attacks against nlp models with semantic-preserving improvements,” in Annual computer security applications conference , 2021, pp. 554–569
2021
Later among the works it cites.
L. Xu, Y. Chen, G. Cui, H. Gao, and Z. Liu, “Exploring the universal vulnerability of prompt-based learning paradigm,” arXiv preprint arXiv:2204.05239 , 2022
Original
2022
Later among the works it cites.
X. Cai, H. Xu, S. Xu, Y. Zhang et al. , “Badprompt: Backdoor attacks on continuous prompts,” Advances in Neural Information Processing Systems , vol. 35, pp. 37 068–37 080, 2022
2022
Later among the works it cites.
H. Touvron, T. Lavril, G. Izacard, X. Martinet, M.-A. Lachaux, T. Lacroix, B. Rozière, N. Goyal, E. Hambro, F. Azhar et al. , “Llama: Open and efficient foundation language models,” arXiv preprint arXiv:2302.13971 , 2023
Original
2023
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…

2021

Cited alongside, same era.

X. L. Li and P. Liang, “Prefix-tuning: Optimizing continuous prompts for generation,” arXiv preprint arXiv:2101.00190 , 2021

2021

Cited alongside, same era.

B. Lester, R. Al-Rfou, and N. Constant, “The power of scale for parameter-efficient prompt tuning,” in Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021 , M. Moens, X. Huang, L. Specia, and S. W. Yih, Eds. Association for Computational Linguistics, 2021, pp. 3045–3059

2021

Cited alongside, same era.

H. Yao, J. Lou, K. Ren, and Z. Qin, “Promptcare: Prompt copyright protection by watermark injection and verification,” arXiv preprint arXiv:2308.02816 , 2023

2023

Closest in time.

K. Mei, Z. Li, Z. Wang, Y. Zhang, and S. Ma, “Notable: Transferable backdoor attacks against prompt-based nlp models,” arXiv preprint arXiv:2305.17826 , 2023

2023

Closest in time.