@inproceedings{chen-etal-2023-towards,
title = "Towards Imperceptible Document Manipulations against Neural Ranking Models",
author = "Chen, Xuanang and
He, Ben and
Ye, Zheng and
Sun, Le and
Sun, Yingfei",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.416",
doi = "10.18653/v1/2023.findings-acl.416",
pages = "6648--6664",
abstract = "Adversarial attacks have gained traction in order to identify vulnerabilities in neural ranking models (NRMs), but current attack methods often introduce noticeable errors. Moreover, current methods rely heavily on using a well-imitated surrogate NRM to guarantee the attack effect, making them difficult to use in practice. This paper proposes a framework called Imperceptible DocumEnt Manipulation (IDEM) to produce adversarial documents that are less noticeable to both algorithms and humans. IDEM instructs a well-established generative language model like BART to generate error-free connection sentences, and employs a separate position-wise merging strategy to balance between relevance and coherence of the perturbed text. Evaluation results on the MS MARCO benchmark demonstrate that IDEM outperforms strong baselines while preserving fluency and correctness of the target documents. Furthermore, the separation of adversarial text generation from the surrogate NRM makes IDEM more robust and less affected by the quality of the surrogate NRM.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2023-towards">
<titleInfo>
<title>Towards Imperceptible Document Manipulations against Neural Ranking Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuanang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingfei</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Adversarial attacks have gained traction in order to identify vulnerabilities in neural ranking models (NRMs), but current attack methods often introduce noticeable errors. Moreover, current methods rely heavily on using a well-imitated surrogate NRM to guarantee the attack effect, making them difficult to use in practice. This paper proposes a framework called Imperceptible DocumEnt Manipulation (IDEM) to produce adversarial documents that are less noticeable to both algorithms and humans. IDEM instructs a well-established generative language model like BART to generate error-free connection sentences, and employs a separate position-wise merging strategy to balance between relevance and coherence of the perturbed text. Evaluation results on the MS MARCO benchmark demonstrate that IDEM outperforms strong baselines while preserving fluency and correctness of the target documents. Furthermore, the separation of adversarial text generation from the surrogate NRM makes IDEM more robust and less affected by the quality of the surrogate NRM.</abstract>
<identifier type="citekey">chen-etal-2023-towards</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.416</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.416</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>6648</start>
<end>6664</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Imperceptible Document Manipulations against Neural Ranking Models
%A Chen, Xuanang
%A He, Ben
%A Ye, Zheng
%A Sun, Le
%A Sun, Yingfei
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F chen-etal-2023-towards
%X Adversarial attacks have gained traction in order to identify vulnerabilities in neural ranking models (NRMs), but current attack methods often introduce noticeable errors. Moreover, current methods rely heavily on using a well-imitated surrogate NRM to guarantee the attack effect, making them difficult to use in practice. This paper proposes a framework called Imperceptible DocumEnt Manipulation (IDEM) to produce adversarial documents that are less noticeable to both algorithms and humans. IDEM instructs a well-established generative language model like BART to generate error-free connection sentences, and employs a separate position-wise merging strategy to balance between relevance and coherence of the perturbed text. Evaluation results on the MS MARCO benchmark demonstrate that IDEM outperforms strong baselines while preserving fluency and correctness of the target documents. Furthermore, the separation of adversarial text generation from the surrogate NRM makes IDEM more robust and less affected by the quality of the surrogate NRM.
%R 10.18653/v1/2023.findings-acl.416
%U https://aclanthology.org/2023.findings-acl.416
%U https://doi.org/10.18653/v1/2023.findings-acl.416
%P 6648-6664
Markdown (Informal)
[Towards Imperceptible Document Manipulations against Neural Ranking Models](https://aclanthology.org/2023.findings-acl.416) (Chen et al., Findings 2023)
ACL