On the Security Risks of AutoML

Ren Pang, Zhaohan Xi, Shouling Ji, Xiapu Luo, Ting Wang

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

7 Citations (Scopus)

Abstract

Neural architecture search (NAS) represents an emerging machine learning (ML) paradigm that automatically searches for model architectures tailored to given tasks, which significantly simplifies the development of ML systems and propels the trend of ML democratization. Yet, thus far little is known about the potential security risks incurred by NAS, which is concerning given the increasing use of NAS-generated models in critical domains.

This work represents a solid initial step towards bridging the gap. First, through an extensive empirical study of 10 popular NAS methods, we show that compared with their manually designed counterparts, NAS-generated models tend to suffer greater vulnerabilities to various malicious manipulations (e.g., adversarial evasion, model poisoning, functionality stealing). Further, with both empirical and analytical evidence, we provide possible explanations for such phenomena: given the prohibitive search space and training cost, most NAS methods favor models that converge fast at early training stages; this preference results in architectural properties associated with attack vulnerabilities (e.g., high loss smoothness, low gradient variance). Our findings not only reveal the relationships between model characteristics and attack vulnerabilities but also suggest the inherent connections underlying different attacks. Finally, we discuss potential remedies to mitigate such drawbacks, including increasing cell depth and suppressing skip connects, which lead to several promising research directions.
Original languageEnglish
Title of host publicationProceedings of the 31st USENIX Security Symposium (USENIX SEC)
PublisherUSENIX
Pages3953-3970
Publication statusPublished - Aug 2022
EventUSENIX Security Symposium - Boston Marriott Copley Place, Boston, United States
Duration: 10 Aug 202212 Aug 2022
Conference number: 31
https://www.usenix.org/conference/usenixsecurity22

Forum/Symposium

Forum/SymposiumUSENIX Security Symposium
Abbreviated titleUSENIX SEC
Country/TerritoryUnited States
CityBoston
Period10/08/2212/08/22
Internet address

Fingerprint

Dive into the research topics of 'On the Security Risks of AutoML'. Together they form a unique fingerprint.

Cite this