@inproceedings{samadi-etal-2021-attacks,
title = "Attacks against Ranking Algorithms with Text Embeddings: {A} Case Study on Recruitment Algorithms",
author = "Samadi, Anahita and
Banerjee, Debapriya and
Nilizadeh, Shirin",
editor = "Bastings, Jasmijn and
Belinkov, Yonatan and
Dupoux, Emmanuel and
Giulianelli, Mario and
Hupkes, Dieuwke and
Pinter, Yuval and
Sajjad, Hassan",
booktitle = "Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.blackboxnlp-1.36",
doi = "10.18653/v1/2021.blackboxnlp-1.36",
pages = "457--467",
abstract = "Recently, some studies have shown that text classification tasks are vulnerable to poisoning and evasion attacks. However, little work has investigated attacks against decision-making algorithms that use text embeddings, and their output is a ranking. In this paper, we focus on ranking algorithms for the recruitment process that employ text embeddings for ranking applicants{'} resumes when compared to a job description. We demonstrate both white-box and black-box attacks that identify text items that, based on their location in embedding space, have a significant contribution in increasing the similarity score between a resume and a job description. The adversary then uses these text items to improve the ranking of their resume among others. We tested recruitment algorithms that use the similarity scores obtained from Universal Sentence Encoder (USE) and Term Frequency{--}Inverse Document Frequency (TF-IDF) vectors. Our results show that in both adversarial settings, on average the attacker is successful. We also found that attacks against TF-IDF are more successful compared to USE.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="samadi-etal-2021-attacks">
<titleInfo>
<title>Attacks against Ranking Algorithms with Text Embeddings: A Case Study on Recruitment Algorithms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anahita</namePart>
<namePart type="family">Samadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debapriya</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shirin</namePart>
<namePart type="family">Nilizadeh</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 Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jasmijn</namePart>
<namePart type="family">Bastings</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Belinkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmanuel</namePart>
<namePart type="family">Dupoux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="family">Giulianelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dieuwke</namePart>
<namePart type="family">Hupkes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuval</namePart>
<namePart type="family">Pinter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sajjad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, some studies have shown that text classification tasks are vulnerable to poisoning and evasion attacks. However, little work has investigated attacks against decision-making algorithms that use text embeddings, and their output is a ranking. In this paper, we focus on ranking algorithms for the recruitment process that employ text embeddings for ranking applicants’ resumes when compared to a job description. We demonstrate both white-box and black-box attacks that identify text items that, based on their location in embedding space, have a significant contribution in increasing the similarity score between a resume and a job description. The adversary then uses these text items to improve the ranking of their resume among others. We tested recruitment algorithms that use the similarity scores obtained from Universal Sentence Encoder (USE) and Term Frequency–Inverse Document Frequency (TF-IDF) vectors. Our results show that in both adversarial settings, on average the attacker is successful. We also found that attacks against TF-IDF are more successful compared to USE.</abstract>
<identifier type="citekey">samadi-etal-2021-attacks</identifier>
<identifier type="doi">10.18653/v1/2021.blackboxnlp-1.36</identifier>
<location>
<url>https://aclanthology.org/2021.blackboxnlp-1.36</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>457</start>
<end>467</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Attacks against Ranking Algorithms with Text Embeddings: A Case Study on Recruitment Algorithms
%A Samadi, Anahita
%A Banerjee, Debapriya
%A Nilizadeh, Shirin
%Y Bastings, Jasmijn
%Y Belinkov, Yonatan
%Y Dupoux, Emmanuel
%Y Giulianelli, Mario
%Y Hupkes, Dieuwke
%Y Pinter, Yuval
%Y Sajjad, Hassan
%S Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F samadi-etal-2021-attacks
%X Recently, some studies have shown that text classification tasks are vulnerable to poisoning and evasion attacks. However, little work has investigated attacks against decision-making algorithms that use text embeddings, and their output is a ranking. In this paper, we focus on ranking algorithms for the recruitment process that employ text embeddings for ranking applicants’ resumes when compared to a job description. We demonstrate both white-box and black-box attacks that identify text items that, based on their location in embedding space, have a significant contribution in increasing the similarity score between a resume and a job description. The adversary then uses these text items to improve the ranking of their resume among others. We tested recruitment algorithms that use the similarity scores obtained from Universal Sentence Encoder (USE) and Term Frequency–Inverse Document Frequency (TF-IDF) vectors. Our results show that in both adversarial settings, on average the attacker is successful. We also found that attacks against TF-IDF are more successful compared to USE.
%R 10.18653/v1/2021.blackboxnlp-1.36
%U https://aclanthology.org/2021.blackboxnlp-1.36
%U https://doi.org/10.18653/v1/2021.blackboxnlp-1.36
%P 457-467
Markdown (Informal)
[Attacks against Ranking Algorithms with Text Embeddings: A Case Study on Recruitment Algorithms](https://aclanthology.org/2021.blackboxnlp-1.36) (Samadi et al., BlackboxNLP 2021)
ACL