Exploring the Universal Vulnerability of Prompt-based Learning Paradigm
Open accessThe DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting.However, we find that this learning paradigm inherits the vulnerability from the pre-training stage, where model predictions can be misled by inserting certain triggers into the text.In this paper, we explore this universal vulnerability by either injecting backdoor triggers or searching for adversarial triggers on pre-trained language models using only plain text.In both scenarios, we demonstrate that our triggers can totally control or severely decrease the performance of prompt-based models fine-tuned on arbitrary downstream tasks, reflecting the universal vulnerability of the prompt-based learning paradigm.Further experiments show that adversarial triggers have good transferability among language models.We also find conventional fine-tuning models are not vulnerable to adversarial triggers constructed from pre-trained language models.We conclude by proposing a potential solution to mitigate our attack methods.Code and data are publicly available.1
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2021) · arXiv · doi:10.48550/arxiv.2107.13586 · Cited by 4,352
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5446 · Cited by 4,222
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.243 · Cited by 3,096
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · arXiv · doi:10.48550/arxiv.2104.08691 · Cited by 3,092
Prefix-Tuning: Optimizing Continuous Prompts for Generation
Li, X. L., & Liang, P. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.353 · Cited by 2,473
Language Models as Knowledge Bases?
Petroni, F., Rocktäschel, T., Riedel, S., Lewis, P., Bakhtin, A., Wu, Y., & Miller, A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1250 · Cited by 1,834
Making Pre-trained Language Models Better Few-shot Learners
Gao, T., Fisch, A., & Chen, D. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.295 · Cited by 1,380
Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference
Schick, T., & Schütze, H. (2021) · Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume · doi:10.18653/v1/2021.eacl-main.20 · Cited by 1,305
Cited by
Security and Privacy Challenges of Large Language Models: A Survey
Das, B. C., Amini, M. H., & Wu, Y. (2025) · ACM Computing Surveys · doi:10.1145/3712001 · Cited by 445
A systematic survey of prompt engineering on vision-language foundation models
Gu, J., Han, Z., Chen, S., Beirami, A., He, B., Zhang, G., Liao, R., Qin, Y., Tresp, V., & Torr, P. (2023) · arXiv · doi:10.48550/arxiv.2307.12980 · Cited by 280
Medical large language models are vulnerable to data-poisoning attacks
Alber, D. A., Yang, Z., Alyakin, A., Yang, E., Rai, S., Valliani, A. A., Zhang, J., Rosenbaum, G. R., Amend-Thomas, A. K., Kurland, D. B., et al. (2025) · Nature Medicine · doi:10.1038/s41591-024-03445-1 · Cited by 242
Learning to Prompt in the Classroom to Understand AI Limits: A Pilot Study
Theophilou, E., Koyutürk, C., Yavari, M., Bursic, S., Donabauer, G., Telari, A., Testa, A., Boiano, R., Hernandez-Leo, D., Ruskov, M., et al. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-47546-7_33 · Cited by 58
Jatmo: Prompt Injection Defense by Task-Specific Finetuning
Piet, J., Alrashed, M., Sitawarin, C., Chen, S., Wei, Z., Sun, E., Alomair, B., & Wagner, D. (2023) · arXiv · doi:10.48550/arxiv.2312.17673 · Cited by 54
Metadata
- Authors
- Xu, L., Chen, Y., Cui, G., Gao, H., & Liu, Z.
- Venue
- Findings of the Association for Computational Linguistics: NAACL 2022
- Published
- 2022
- Pages
- 1799-1810
- OpenAlex
- W4224903411
- Cited by
- 45
- References
- 15
- FWCI
- 6.14
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Exploring the Universal Vulnerability of Prompt-based Learning Paradigm. https://app.cochat.ai/papers/10.18653/v1/2022.findings-naacl.137
- The paper
- Xu, L., Chen, Y., Cui, G., Gao, H., & Liu, Z. (2022). Exploring the Universal Vulnerability of Prompt-based Learning Paradigm. Findings of the Association for Computational Linguistics: NAACL 2022. https://doi.org/10.18653/v1/2022.findings-naacl.137
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.