<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rusert-2024-vertattack">
    <titleInfo>
        <title>VertAttack: Taking Advantage of Text Classifiers’ Horizontal Vision</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jonathan</namePart>
        <namePart type="family">Rusert</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kevin</namePart>
            <namePart type="family">Duh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Helena</namePart>
            <namePart type="family">Gomez</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>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Mexico City, Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Text classification systems have continuouslyimproved in performance over the years. How-ever, nearly all current SOTA classifiers have asimilar shortcoming, they process text in a hor-izontal manner. Vertically written words willnot be recognized by a classifier. In contrast,humans are easily able to recognize and readwords written both horizontally and vertically.Hence, a human adversary could write problem-atic words vertically and the meaning wouldstill be preserved to other humans. We simulatesuch an attack, VertAttack. VertAttack identifieswhich words a classifier is reliant on and thenrewrites those words vertically. We find thatVertAttack is able to greatly drop the accuracyof 4 different transformer models on 5 datasets.For example, on the SST2 dataset, VertAttackis able to drop RoBERTa’s accuracy from 94 to13%. Furthermore, since VertAttack does notreplace the word, meaning is easily preserved.We verify this via a human study and find thatcrowdworkers are able to correctly label 77%perturbed texts perturbed, compared to 81% ofthe original texts. We believe VertAttack offersa look into how humans might circumvent clas-sifiers in the future and thus inspire a look intomore robust algorithms.</abstract>
    <identifier type="citekey">rusert-2024-vertattack</identifier>
    <location>
        <url>https://aclanthology.org/2024.naacl-long.41</url>
    </location>
    <part>
        <date>2024-06</date>
        <extent unit="page">
            <start>719</start>
            <end>732</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T VertAttack: Taking Advantage of Text Classifiers’ Horizontal Vision
%A Rusert, Jonathan
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F rusert-2024-vertattack
%X Text classification systems have continuouslyimproved in performance over the years. How-ever, nearly all current SOTA classifiers have asimilar shortcoming, they process text in a hor-izontal manner. Vertically written words willnot be recognized by a classifier. In contrast,humans are easily able to recognize and readwords written both horizontally and vertically.Hence, a human adversary could write problem-atic words vertically and the meaning wouldstill be preserved to other humans. We simulatesuch an attack, VertAttack. VertAttack identifieswhich words a classifier is reliant on and thenrewrites those words vertically. We find thatVertAttack is able to greatly drop the accuracyof 4 different transformer models on 5 datasets.For example, on the SST2 dataset, VertAttackis able to drop RoBERTa’s accuracy from 94 to13%. Furthermore, since VertAttack does notreplace the word, meaning is easily preserved.We verify this via a human study and find thatcrowdworkers are able to correctly label 77%perturbed texts perturbed, compared to 81% ofthe original texts. We believe VertAttack offersa look into how humans might circumvent clas-sifiers in the future and thus inspire a look intomore robust algorithms.
%U https://aclanthology.org/2024.naacl-long.41
%P 719-732

Markdown (Informal)

[VertAttack: Taking Advantage of Text Classifiers’ Horizontal Vision](https://aclanthology.org/2024.naacl-long.41) (Rusert, NAACL 2024)

• VertAttack: Taking Advantage of Text Classifiers’ Horizontal Vision (Rusert, NAACL 2024)

ACL

• Jonathan Rusert. 2024. VertAttack: Taking Advantage of Text Classifiers’ Horizontal Vision. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 719–732, Mexico City, Mexico. Association for Computational Linguistics.