<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="olivier-raj-2021-sequential">
    <titleInfo>
        <title>Sequential Randomized Smoothing for Adversarially Robust Speech Recognition</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Raphael</namePart>
        <namePart type="family">Olivier</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bhiksha</namePart>
        <namePart type="family">Raj</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 2021 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>While Automatic Speech Recognition has been shown to be vulnerable to adversarial attacks, defenses against these attacks are still lagging. Existing, naive defenses can be partially broken with an adaptive attack. In classification tasks, the Randomized Smoothing paradigm has been shown to be effective at defending models. However, it is difficult to apply this paradigm to ASR tasks, due to their complexity and the sequential nature of their outputs. Our paper overcomes some of these challenges by leveraging speech-specific tools like enhancement and ROVER voting to design an ASR model that is robust to perturbations. We apply adaptive versions of state-of-the-art attacks, such as the Imperceptible ASR attack, to our model, and show that our strongest defense is robust to all attacks that use inaudible noise, and can only be broken with very high distortion.</abstract>
    <identifier type="citekey">olivier-raj-2021-sequential</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.514</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.514</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>6372</start>
            <end>6386</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Sequential Randomized Smoothing for Adversarially Robust Speech Recognition
%A Olivier, Raphael
%A Raj, Bhiksha
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F olivier-raj-2021-sequential
%X While Automatic Speech Recognition has been shown to be vulnerable to adversarial attacks, defenses against these attacks are still lagging. Existing, naive defenses can be partially broken with an adaptive attack. In classification tasks, the Randomized Smoothing paradigm has been shown to be effective at defending models. However, it is difficult to apply this paradigm to ASR tasks, due to their complexity and the sequential nature of their outputs. Our paper overcomes some of these challenges by leveraging speech-specific tools like enhancement and ROVER voting to design an ASR model that is robust to perturbations. We apply adaptive versions of state-of-the-art attacks, such as the Imperceptible ASR attack, to our model, and show that our strongest defense is robust to all attacks that use inaudible noise, and can only be broken with very high distortion.
%R 10.18653/v1/2021.emnlp-main.514
%U https://aclanthology.org/2021.emnlp-main.514
%U https://doi.org/10.18653/v1/2021.emnlp-main.514
%P 6372-6386

Markdown (Informal)

[Sequential Randomized Smoothing for Adversarially Robust Speech Recognition](https://aclanthology.org/2021.emnlp-main.514) (Olivier & Raj, EMNLP 2021)

• Sequential Randomized Smoothing for Adversarially Robust Speech Recognition (Olivier & Raj, EMNLP 2021)

ACL

• Raphael Olivier and Bhiksha Raj. 2021. Sequential Randomized Smoothing for Adversarially Robust Speech Recognition. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6372–6386, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.