@inproceedings{sabir-etal-2021-reinforcebug,
title = "{R}einforce{B}ug: A Framework to Generate Adversarial Textual Examples",
author = "Sabir, Bushra and
Babar, Muhammad Ali and
Gaire, Raj",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.477",
doi = "10.18653/v1/2021.naacl-main.477",
pages = "5954--5964",
abstract = "Adversarial Examples (AEs) generated by perturbingining examples are useful in improving the robustness of Deep Learning (DL) based models. Most prior works generate AEs that are either unconscionable due to lexical errors or semantically and functionally deviant from original examples. In this paper, we present ReinforceBug, a reinforcement learning framework, that learns a policy that is transferable on unseen datasets and generates utility-preserving and transferable (on other models) AEs. Our experiments show that ReinforceBug is on average 10{\%} more successful as compared to the state-of the-art attack TextFooler. Moreover, the target models have on average 73.64{\%} confidence in wrong prediction, the generated AEs preserve the functional equivalence and semantic similarity (83.38{\%}) to their original counterparts, and are transferable on other models with an average success rate of 46{\%}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sabir-etal-2021-reinforcebug">
<titleInfo>
<title>ReinforceBug: A Framework to Generate Adversarial Textual Examples</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bushra</namePart>
<namePart type="family">Sabir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Ali</namePart>
<namePart type="family">Babar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Gaire</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Adversarial Examples (AEs) generated by perturbingining examples are useful in improving the robustness of Deep Learning (DL) based models. Most prior works generate AEs that are either unconscionable due to lexical errors or semantically and functionally deviant from original examples. In this paper, we present ReinforceBug, a reinforcement learning framework, that learns a policy that is transferable on unseen datasets and generates utility-preserving and transferable (on other models) AEs. Our experiments show that ReinforceBug is on average 10% more successful as compared to the state-of the-art attack TextFooler. Moreover, the target models have on average 73.64% confidence in wrong prediction, the generated AEs preserve the functional equivalence and semantic similarity (83.38%) to their original counterparts, and are transferable on other models with an average success rate of 46%</abstract>
<identifier type="citekey">sabir-etal-2021-reinforcebug</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.477</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.477</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>5954</start>
<end>5964</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReinforceBug: A Framework to Generate Adversarial Textual Examples
%A Sabir, Bushra
%A Babar, Muhammad Ali
%A Gaire, Raj
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F sabir-etal-2021-reinforcebug
%X Adversarial Examples (AEs) generated by perturbingining examples are useful in improving the robustness of Deep Learning (DL) based models. Most prior works generate AEs that are either unconscionable due to lexical errors or semantically and functionally deviant from original examples. In this paper, we present ReinforceBug, a reinforcement learning framework, that learns a policy that is transferable on unseen datasets and generates utility-preserving and transferable (on other models) AEs. Our experiments show that ReinforceBug is on average 10% more successful as compared to the state-of the-art attack TextFooler. Moreover, the target models have on average 73.64% confidence in wrong prediction, the generated AEs preserve the functional equivalence and semantic similarity (83.38%) to their original counterparts, and are transferable on other models with an average success rate of 46%
%R 10.18653/v1/2021.naacl-main.477
%U https://aclanthology.org/2021.naacl-main.477
%U https://doi.org/10.18653/v1/2021.naacl-main.477
%P 5954-5964
Markdown (Informal)
[ReinforceBug: A Framework to Generate Adversarial Textual Examples](https://aclanthology.org/2021.naacl-main.477) (Sabir et al., NAACL 2021)
ACL
- Bushra Sabir, Muhammad Ali Babar, and Raj Gaire. 2021. ReinforceBug: A Framework to Generate Adversarial Textual Examples. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5954–5964, Online. Association for Computational Linguistics.