A Sweet Rabbit Hole by DARCY: Using Honeypots to Detect Universal Trigger’s Adversarial Attacks

Thai Le, Noseong Park, Dongwon Lee


Abstract
The Universal Trigger (UniTrigger) is a recently-proposed powerful adversarial textual attack method. Utilizing a learning-based mechanism, UniTrigger generates a fixed phrase that, when added to any benign inputs, can drop the prediction accuracy of a textual neural network (NN) model to near zero on a target class. To defend against this attack that can cause significant harm, in this paper, we borrow the “honeypot” concept from the cybersecurity community and propose DARCY, a honeypot-based defense framework against UniTrigger. DARCY greedily searches and injects multiple trapdoors into an NN model to “bait and catch” potential attacks. Through comprehensive experiments across four public datasets, we show that DARCY detects UniTrigger’s adversarial attacks with up to 99% TPR and less than 2% FPR in most cases, while maintaining the prediction accuracy (in F1) for clean inputs within a 1% margin. We also demonstrate that DARCY with multiple trapdoors is also robust to a diverse set of attack scenarios with attackers’ varying levels of knowledge and skills. We release the source code of DARCY at: https://github.com/lethaiq/ACL2021-DARCY-HoneypotDefenseNLP.
Anthology ID:
2021.acl-long.296
Volume:
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)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3831–3844
Language:
URL:
https://aclanthology.org/2021.acl-long.296
DOI:
10.18653/v1/2021.acl-long.296
Bibkey:
Cite (ACL):
Thai Le, Noseong Park, and Dongwon Lee. 2021. A Sweet Rabbit Hole by DARCY: Using Honeypots to Detect Universal Trigger’s Adversarial Attacks. In 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), pages 3831–3844, Online. Association for Computational Linguistics.
Cite (Informal):
A Sweet Rabbit Hole by DARCY: Using Honeypots to Detect Universal Trigger’s Adversarial Attacks (Le et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.296.pdf
Video:
 https://aclanthology.org/2021.acl-long.296.mp4