@inproceedings{jia-etal-2019-certified,
title = "Certified Robustness to Adversarial Word Substitutions",
author = {Jia, Robin and
Raghunathan, Aditi and
G{\"o}ksel, Kerem and
Liang, Percy},
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1423/",
doi = "10.18653/v1/D19-1423",
pages = "4129--4142",
abstract = "State-of-the-art NLP models can often be fooled by adversaries that apply seemingly innocuous label-preserving transformations (e.g., paraphrasing) to input text. The number of possible transformations scales exponentially with text length, so data augmentation cannot cover all transformations of an input. This paper considers one exponentially large family of label-preserving transformations, in which every word in the input can be replaced with a similar word. We train the first models that are provably robust to all word substitutions in this family. Our training procedure uses Interval Bound Propagation (IBP) to minimize an upper bound on the worst-case loss that any combination of word substitutions can induce. To evaluate models' robustness to these transformations, we measure accuracy on adversarially chosen word substitutions applied to test examples. Our IBP-trained models attain 75{\%} adversarial accuracy on both sentiment analysis on IMDB and natural language inference on SNLI; in comparison, on IMDB, models trained normally and ones trained with data augmentation achieve adversarial accuracy of only 12{\%} and 41{\%}, respectively."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jia-etal-2019-certified">
<titleInfo>
<title>Certified Robustness to Adversarial Word Substitutions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Robin</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditi</namePart>
<namePart type="family">Raghunathan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kerem</namePart>
<namePart type="family">Göksel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Percy</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>State-of-the-art NLP models can often be fooled by adversaries that apply seemingly innocuous label-preserving transformations (e.g., paraphrasing) to input text. The number of possible transformations scales exponentially with text length, so data augmentation cannot cover all transformations of an input. This paper considers one exponentially large family of label-preserving transformations, in which every word in the input can be replaced with a similar word. We train the first models that are provably robust to all word substitutions in this family. Our training procedure uses Interval Bound Propagation (IBP) to minimize an upper bound on the worst-case loss that any combination of word substitutions can induce. To evaluate models’ robustness to these transformations, we measure accuracy on adversarially chosen word substitutions applied to test examples. Our IBP-trained models attain 75% adversarial accuracy on both sentiment analysis on IMDB and natural language inference on SNLI; in comparison, on IMDB, models trained normally and ones trained with data augmentation achieve adversarial accuracy of only 12% and 41%, respectively.</abstract>
<identifier type="citekey">jia-etal-2019-certified</identifier>
<identifier type="doi">10.18653/v1/D19-1423</identifier>
<location>
<url>https://aclanthology.org/D19-1423/</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>4129</start>
<end>4142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Certified Robustness to Adversarial Word Substitutions
%A Jia, Robin
%A Raghunathan, Aditi
%A Göksel, Kerem
%A Liang, Percy
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F jia-etal-2019-certified
%X State-of-the-art NLP models can often be fooled by adversaries that apply seemingly innocuous label-preserving transformations (e.g., paraphrasing) to input text. The number of possible transformations scales exponentially with text length, so data augmentation cannot cover all transformations of an input. This paper considers one exponentially large family of label-preserving transformations, in which every word in the input can be replaced with a similar word. We train the first models that are provably robust to all word substitutions in this family. Our training procedure uses Interval Bound Propagation (IBP) to minimize an upper bound on the worst-case loss that any combination of word substitutions can induce. To evaluate models’ robustness to these transformations, we measure accuracy on adversarially chosen word substitutions applied to test examples. Our IBP-trained models attain 75% adversarial accuracy on both sentiment analysis on IMDB and natural language inference on SNLI; in comparison, on IMDB, models trained normally and ones trained with data augmentation achieve adversarial accuracy of only 12% and 41%, respectively.
%R 10.18653/v1/D19-1423
%U https://aclanthology.org/D19-1423/
%U https://doi.org/10.18653/v1/D19-1423
%P 4129-4142
Markdown (Informal)
[Certified Robustness to Adversarial Word Substitutions](https://aclanthology.org/D19-1423/) (Jia et al., EMNLP-IJCNLP 2019)
ACL
- Robin Jia, Aditi Raghunathan, Kerem Göksel, and Percy Liang. 2019. Certified Robustness to Adversarial Word Substitutions. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4129–4142, Hong Kong, China. Association for Computational Linguistics.