%0 Conference Proceedings
%T Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers
%A You, Wencong
%A Hammoudeh, Zayd
%A Lowd, Daniel
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F you-etal-2023-large
%X Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled. Our attack, LLMBkd, leverages language models to automatically insert diverse style-based triggers into texts. We also propose a poison selection technique to improve the effectiveness of both LLMBkd as well as existing textual backdoor attacks. Lastly, we describe REACT, a baseline defense to mitigate backdoor attacks via antidote training examples. Our evaluations demonstrate LLMBkd’s effectiveness and efficiency, where we consistently achieve high attack success rates across a wide range of styles with little effort and no model training.
%R 10.18653/v1/2023.findings-emnlp.833
%U https://aclanthology.org/2023.findings-emnlp.833
%U https://doi.org/10.18653/v1/2023.findings-emnlp.833
%P 12499-12527