<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maheshwary-etal-2021-strong">
    <titleInfo>
        <title>A Strong Baseline for Query Efficient Attacks in a Black Box Setting</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rishabh</namePart>
        <namePart type="family">Maheshwary</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Saket</namePart>
        <namePart type="family">Maheshwary</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vikram</namePart>
        <namePart type="family">Pudi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Existing black box search methods have achieved high success rate in generating adversarial attacks against NLP models. However, such search methods are inefficient as they do not consider the amount of queries required to generate adversarial attacks. Also, prior attacks do not maintain a consistent search space while comparing different search methods. In this paper, we propose a query efficient attack strategy to generate plausible adversarial examples on text classification and entailment tasks. Our attack jointly leverages attention mechanism and locality sensitive hashing (LSH) to reduce the query count. We demonstrate the efficacy of our approach by comparing our attack with four baselines across three different search spaces. Further, we benchmark our results across the same search space used in prior attacks. In comparison to attacks proposed, on an average, we are able to reduce the query count by 75% across all datasets and target models. We also demonstrate that our attack achieves a higher success rate when compared to prior attacks in a limited query setting.</abstract>
    <identifier type="citekey">maheshwary-etal-2021-strong</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.661</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.661/</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>8396</start>
            <end>8409</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Strong Baseline for Query Efficient Attacks in a Black Box Setting
%A Maheshwary, Rishabh
%A Maheshwary, Saket
%A Pudi, Vikram
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F maheshwary-etal-2021-strong
%X Existing black box search methods have achieved high success rate in generating adversarial attacks against NLP models. However, such search methods are inefficient as they do not consider the amount of queries required to generate adversarial attacks. Also, prior attacks do not maintain a consistent search space while comparing different search methods. In this paper, we propose a query efficient attack strategy to generate plausible adversarial examples on text classification and entailment tasks. Our attack jointly leverages attention mechanism and locality sensitive hashing (LSH) to reduce the query count. We demonstrate the efficacy of our approach by comparing our attack with four baselines across three different search spaces. Further, we benchmark our results across the same search space used in prior attacks. In comparison to attacks proposed, on an average, we are able to reduce the query count by 75% across all datasets and target models. We also demonstrate that our attack achieves a higher success rate when compared to prior attacks in a limited query setting.
%R 10.18653/v1/2021.emnlp-main.661
%U https://aclanthology.org/2021.emnlp-main.661/
%U https://doi.org/10.18653/v1/2021.emnlp-main.661
%P 8396-8409

Markdown (Informal)

[A Strong Baseline for Query Efficient Attacks in a Black Box Setting](https://aclanthology.org/2021.emnlp-main.661/) (Maheshwary et al., EMNLP 2021)

• A Strong Baseline for Query Efficient Attacks in a Black Box Setting (Maheshwary et al., EMNLP 2021)

ACL

• Rishabh Maheshwary, Saket Maheshwary, and Vikram Pudi. 2021. A Strong Baseline for Query Efficient Attacks in a Black Box Setting. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8396–8409, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.