CISPA
Browse
usenixsecurity23-mink.pdf (480 kB)

"Security is not my field, I'm a stats guy": A Qualitative Root Cause Analysis of Barriers to Adversarial Machine Learning Defenses in Industry.

Download (480 kB)
conference contribution
posted on 2024-03-20, 10:28 authored by Jaron Mink, Harjot KaurHarjot Kaur, Juliane SchmüserJuliane Schmüser, Sascha FahlSascha Fahl, Yasemin Acar
Adversarial machine learning (AML) has the potential to leak training data, force arbitrary classifications, and greatly degrade overall performance of machine learning models, all of which academics and companies alike consider as serious issues. Despite this, seminal work has found that most organizations insufficiently protect against such threats. While the lack of defenses to AML is most commonly attributed to missing knowledge, it is unknown why mitigations are unrealized in industry projects. To better understand the reasons behind the lack of deployed AML defenses, we conduct semi-structured interviews (n=21) with data scientists and data engineers to explore what barriers impede the effective implementation of such defenses. We find that practitioners’ ability to deploy defenses is hampered by three primary factors: a lack of institutional motivation and educational resources for these concepts, an inability to adequately assess their AML risk and make subsequent decisions, and organizational structures and goals that discourage implementation in favor of other objectives. We conclude by discussing practical recommendations for companies and practitioners to be made more aware of these risks, and better prepared to respond.

History

Primary Research Area

  • Empirical and Behavioral Security

Name of Conference

Usenix Security Symposium (USENIX-Security)

Journal

USENIX Security Symposium

Page Range

3763-3780

BibTeX

@conference{Mink:Kaur:Schmüser:Fahl:Acar:2023, title = {"Security is not my field, I'm a stats guy": A Qualitative Root Cause Analysis of Barriers to Adversarial Machine Learning Defenses in Industry.}, author = "Mink, Jaron" AND "Kaur, Harjot" AND "Schmüser, Juliane" AND "Fahl, Sascha" AND "Acar, Yasemin", year = 2023, month = 8, journal = "USENIX Security Symposium", pages = "3763--3780" }

Usage metrics

    Categories

    No categories selected

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC