SoK: Security and Privacy in Machine Learning

Nicolas Papernot, Patrick McDaniel, Arunesh Sinha, Michael P. Wellman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

373 Scopus citations

Abstract

Advances in machine learning (ML) in recent years have enabled a dizzying array of applications such as data analytics, autonomous systems, and security diagnostics. ML is now pervasive - new systems and models are being deployed in every domain imaginable, leading to widespread deployment of software based inference and decision making. There is growing recognition that ML exposes new vulnerabilities in software systems, yet the technical community's understanding of the nature and extent of these vulnerabilities remains limited. We systematize findings on ML security and privacy, focusing on attacks identified on these systems and defenses crafted to date.We articulate a comprehensive threat model for ML, and categorize attacks and defenses within an adversarial framework. Key insights resulting from works both in the ML and security communities are identified and the effectiveness of approaches are related to structural elements of ML algorithms and the data used to train them. In particular, it is apparent that constructing a theoretical understanding of the sensitivity of modern ML algorithms to the data they analyze, à la PAC theory, will foster a science of security and privacy in ML.

Original languageEnglish (US)
Title of host publicationProceedings - 3rd IEEE European Symposium on Security and Privacy, EURO S and P 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages399-414
Number of pages16
ISBN (Electronic)9781538642276
DOIs
StatePublished - Jul 6 2018
Event3rd IEEE European Symposium on Security and Privacy, EURO S and P 2018 - London, United Kingdom
Duration: Apr 24 2018Apr 26 2018

Publication series

NameProceedings - 3rd IEEE European Symposium on Security and Privacy, EURO S and P 2018

Other

Other3rd IEEE European Symposium on Security and Privacy, EURO S and P 2018
Country/TerritoryUnited Kingdom
CityLondon
Period4/24/184/26/18

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'SoK: Security and Privacy in Machine Learning'. Together they form a unique fingerprint.

Cite this