<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gagiano-etal-2021-robustness">
    <titleInfo>
        <title>Robustness Analysis of Grover for Machine-Generated News Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rinaldo</namePart>
        <namePart type="family">Gagiano</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maria</namePart>
        <namePart type="given">Myung-Hee</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiuzhen</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jennifer</namePart>
        <namePart type="family">Biggs</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the The 19th Annual Workshop of the Australasian Language Technology Association</title>
        </titleInfo>
        <originInfo>
            <publisher>Australasian Language Technology Association</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Advancements in Natural Language Generation have raised concerns on its potential misuse for deep fake news. Grover is a model for both generation and detection of neural fake news. While its performance on automatically discriminating neural fake news surpassed GPT-2 and BERT, Grover could face a variety of adversarial attacks to deceive detection. In this work, we present an investigation of Grover’s susceptibility to adversarial attacks such as character-level and word-level perturbations. The experiment results show that even a singular character alteration can cause Grover to fail, affecting up to 97% of target articles with unlimited attack attempts, exposing a lack of robustness. We further analyse these misclassified cases to highlight affected words, identify vulnerability within Grover’s encoder, and perform a novel visualisation of cumulative classification scores to assist in interpreting model behaviour.</abstract>
    <identifier type="citekey">gagiano-etal-2021-robustness</identifier>
    <location>
        <url>https://aclanthology.org/2021.alta-1.12</url>
    </location>
    <part>
        <date>2021-12</date>
        <extent unit="page">
            <start>119</start>
            <end>127</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Robustness Analysis of Grover for Machine-Generated News Detection
%A Gagiano, Rinaldo
%A Kim, Maria Myung-Hee
%A Zhang, Xiuzhen
%A Biggs, Jennifer
%S Proceedings of the The 19th Annual Workshop of the Australasian Language Technology Association
%D 2021
%8 December
%I Australasian Language Technology Association
%C Online
%F gagiano-etal-2021-robustness
%X Advancements in Natural Language Generation have raised concerns on its potential misuse for deep fake news. Grover is a model for both generation and detection of neural fake news. While its performance on automatically discriminating neural fake news surpassed GPT-2 and BERT, Grover could face a variety of adversarial attacks to deceive detection. In this work, we present an investigation of Grover’s susceptibility to adversarial attacks such as character-level and word-level perturbations. The experiment results show that even a singular character alteration can cause Grover to fail, affecting up to 97% of target articles with unlimited attack attempts, exposing a lack of robustness. We further analyse these misclassified cases to highlight affected words, identify vulnerability within Grover’s encoder, and perform a novel visualisation of cumulative classification scores to assist in interpreting model behaviour.
%U https://aclanthology.org/2021.alta-1.12
%P 119-127

Markdown (Informal)

[Robustness Analysis of Grover for Machine-Generated News Detection](https://aclanthology.org/2021.alta-1.12) (Gagiano et al., ALTA 2021)

• Robustness Analysis of Grover for Machine-Generated News Detection (Gagiano et al., ALTA 2021)

ACL

• Rinaldo Gagiano, Maria Myung-Hee Kim, Xiuzhen Zhang, and Jennifer Biggs. 2021. Robustness Analysis of Grover for Machine-Generated News Detection. In Proceedings of the The 19th Annual Workshop of the Australasian Language Technology Association, pages 119–127, Online. Australasian Language Technology Association.