<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chan-etal-2020-poison">
    <titleInfo>
        <title>Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Alvin</namePart>
        <namePart type="family">Chan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yi</namePart>
        <namePart type="family">Tay</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yew-Soon</namePart>
        <namePart type="family">Ong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aston</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Trevor</namePart>
            <namePart type="family">Cohn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulan</namePart>
            <namePart type="family">He</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper demonstrates a fatal vulnerability in natural language inference (NLI) and text classification systems. More concretely, we present a ‘backdoor poisoning’ attack on NLP models. Our poisoning attack utilizes conditional adversarially regularized autoencoder (CARA) to generate poisoned training samples by poison injection in latent space. Just by adding 1% poisoned data, our experiments show that a victim BERT finetuned classifier’s predictions can be steered to the poison target class with success rates of &gt;80% when the input hypothesis is injected with the poison signature, demonstrating that NLI and text classification systems face a huge security risk.</abstract>
    <identifier type="citekey">chan-etal-2020-poison</identifier>
    <identifier type="doi">10.18653/v1/2020.findings-emnlp.373</identifier>
    <location>
        <url>https://aclanthology.org/2020.findings-emnlp.373</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>4175</start>
            <end>4189</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder
%A Chan, Alvin
%A Tay, Yi
%A Ong, Yew-Soon
%A Zhang, Aston
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F chan-etal-2020-poison
%X This paper demonstrates a fatal vulnerability in natural language inference (NLI) and text classification systems. More concretely, we present a ‘backdoor poisoning’ attack on NLP models. Our poisoning attack utilizes conditional adversarially regularized autoencoder (CARA) to generate poisoned training samples by poison injection in latent space. Just by adding 1% poisoned data, our experiments show that a victim BERT finetuned classifier’s predictions can be steered to the poison target class with success rates of >80% when the input hypothesis is injected with the poison signature, demonstrating that NLI and text classification systems face a huge security risk.
%R 10.18653/v1/2020.findings-emnlp.373
%U https://aclanthology.org/2020.findings-emnlp.373
%U https://doi.org/10.18653/v1/2020.findings-emnlp.373
%P 4175-4189

Markdown (Informal)

[Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder](https://aclanthology.org/2020.findings-emnlp.373) (Chan et al., Findings 2020)

• Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder (Chan et al., Findings 2020)

ACL

• Alvin Chan, Yi Tay, Yew-Soon Ong, and Aston Zhang. 2020. Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4175–4189, Online. Association for Computational Linguistics.