White-to-black: Efficient distillation of black-box adversarial attacks

Yotam Gil, Yoav Chai, Or Gorodissky, Jonathan Berant

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Adversarial examples are important for understanding the behavior of neural models, and can improve their robustness through adversarial training. Recent work in natural language processing generated adversarial examples by assuming white-box access to the attacked model, and optimizing the input directly against it (Ebrahimi et al., 2018). In this work, we show that the knowledge implicit in the optimization procedure can be distilled into another more efficient neural network. We train a model to emulate the behavior of a white-box attack and show that it generalizes well across examples. Moreover, it reduces adversarial example generation time by 19x-39x. We also show that our approach transfers to a black-box setting, by attacking The Google Perspective API and exposing its vulnerability. Our attack flips the API-predicted label in 42% of the generated examples, while humans maintain high-accuracy in predicting the gold label.

Original languageEnglish
Title of host publicationLong and Short Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages1373-1379
Number of pages7
ISBN (Electronic)9781950737130
StatePublished - 2019
Event2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019 - Minneapolis, United States
Duration: 2 Jun 20197 Jun 2019

Publication series

NameNAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
Volume1

Conference

Conference2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019
Country/TerritoryUnited States
CityMinneapolis
Period2/06/197/06/19

Fingerprint

Dive into the research topics of 'White-to-black: Efficient distillation of black-box adversarial attacks'. Together they form a unique fingerprint.

Cite this