Abstract
Prompt-based learning has been proved to be an effective way in pre-trained language models (PLMs), especially in low-resource scenarios like few-shot settings. However, the trustworthiness of PLMs is of paramount significance and potential vulnerabilities have been shown in prompt-based templates that could mislead the predictions of language models, causing serious security concerns. In this paper, we will shed light on some vulnerabilities of PLMs, by proposing a prompt-based adversarial attack on manual templates in black box scenarios. First of all, we design character-level and word-level heuristic approaches to break manual templates separately. Then we present a greedy algorithm for the attack based on the above heuristic destructive approaches. Finally, we evaluate our approach with the classification tasks on three variants of BERT series models and eight datasets. And comprehensive experimental results justify the effectiveness of our approach in terms of attack success rate and attack speed.
Supported by Guangdong Provincial Key-Area Research and Development Program (2022B0101010005), Qinghai Provincial Science and Technology Research Program (2021-QY-206), National Natural Science Foundation of China (62071201), and Guangdong Basic and Applied Basic Research Foundation (No.2022A1515010119).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., Neubig, G.: Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput. Surv. 55(9), 1–35 (2023)
Gao, T., Fisch, A., Chen, D.: Making pre-trained language models better few-shot learners. arXiv preprint arXiv:2012.15723 (2020)
Xu, L., Chen, Y., Cui, G., Gao, H., Liu, Z.: Exploring the Universal Vulnerability of Prompt-based Learning Paradigm. arXiv preprint arXiv:2204.05239 (2022)
Shi, Y., Li, P., Yin, C., Han, Z., Zhou, L., Liu, Z.: PromptAttack: prompt-based attack for language models via gradient search. arXiv preprint arXiv:2209.01882 (2022)
Lee, D., Moon, S., Lee, J., Song, H.O.: Query-efficient and scalable black-box adversarial attacks on discrete sequential data via Bayesian optimization. arXiv preprint arXiv:2206.08575 (2022)
Chen, Y., Gao, H., Cui, G., Qi, F., Huang, L., Liu, Z., et al.: Why should adversarial perturbations be imperceptible? rethink the research paradigm in adversarial NLP. arXiv preprint arXiv:2210.10683 (2022)
Devlin, J., Chang, M. W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)
Loshchilov, I., Hutter, F.: Fixing weight decay regularization in Adam. arXiv preprint arXiv: 1711.05101 (2017)
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)
Maas, A.L., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: Proceedings of the 49th annual meeting of the association for computational linguistics: Human language technologies, pp. 142–150. Association for Computer Linguistics, Portland, Oregon, United States (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Tan, Z., Chen, Q., Zhu, W., Huang, Y. (2024). COVER: A Heuristic Greedy Adversarial Attack on Prompt-Based Learning in Language Models. In: Liu, F., Sadanandan, A.A., Pham, D.N., Mursanto, P., Lukose, D. (eds) PRICAI 2023: Trends in Artificial Intelligence. PRICAI 2023. Lecture Notes in Computer Science(), vol 14326. Springer, Singapore. https://doi.org/10.1007/978-981-99-7022-3_30
Download citation
DOI: https://doi.org/10.1007/978-981-99-7022-3_30
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7021-6
Online ISBN: 978-981-99-7022-3
eBook Packages: Computer ScienceComputer Science (R0)