SHIELD: Defending Textual Neural Networks against Multiple Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher

Thai Le, Noseong Park, Dongwon Lee


Abstract
Even though several methods have proposed to defend textual neural network (NN) models against black-box adversarial attacks, they often defend against a specific text perturbation strategy and/or require re-training the models from scratch. This leads to a lack of generalization in practice and redundant computation. In particular, the state-of-the-art transformer models (e.g., BERT, RoBERTa) require great time and computation resources. By borrowing an idea from software engineering, in order to address these limitations, we propose a novel algorithm, SHIELD, which modifies and re-trains only the last layer of a textual NN, and thus it “patches” and “transforms” the NN into a stochastic weighted ensemble of multi-expert prediction heads. Considering that most of current black-box attacks rely on iterative search mechanisms to optimize their adversarial perturbations, SHIELD confuses the attackers by automatically utilizing different weighted ensembles of predictors depending on the input. In other words, SHIELD breaks a fundamental assumption of the attack, which is a victim NN model remains constant during an attack. By conducting comprehensive experiments, we demonstrate that all of CNN, RNN, BERT, and RoBERTa-based textual NNs, once patched by SHIELD, exhibit a relative enhancement of 15%–70% in accuracy on average against 14 different black-box attacks, outperforming 6 defensive baselines across 3 public datasets. All codes are to be released.
Anthology ID:
2022.acl-long.459
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6661–6674
Language:
URL:
https://aclanthology.org/2022.acl-long.459
DOI:
10.18653/v1/2022.acl-long.459
Bibkey:
Cite (ACL):
Thai Le, Noseong Park, and Dongwon Lee. 2022. SHIELD: Defending Textual Neural Networks against Multiple Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6661–6674, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
SHIELD: Defending Textual Neural Networks against Multiple Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher (Le et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.459.pdf
Video:
 https://aclanthology.org/2022.acl-long.459.mp4
Code
 lethaiq/shield-defend-adversarial-texts