A sweet rabbit hole by DARCY: Using honeypots to detect universal trigger's adversarial attacks

Thai Le, Noseong Park, Dongwon Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Scopus citations

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.

Original languageEnglish (US)
Title of host publicationACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages3831-3844
Number of pages14
ISBN (Electronic)9781954085527
StatePublished - 2021
EventJoint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021 - Virtual, Online
Duration: Aug 1 2021Aug 6 2021

Publication series

NameACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference

Conference

ConferenceJoint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021
CityVirtual, Online
Period8/1/218/6/21

All Science Journal Classification (ASJC) codes

  • Software
  • Computational Theory and Mathematics
  • Linguistics and Language
  • Language and Linguistics

Fingerprint

Dive into the research topics of 'A sweet rabbit hole by DARCY: Using honeypots to detect universal trigger's adversarial attacks'. Together they form a unique fingerprint.

Cite this