Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses

Micah Goldblum, Dimitris Tsipras, Chulin Xie, Xinyun Chen, Avi Schwarzschild, Dawn Song, Aleksander Madry, Bo Li, Tom Goldstein

Research output: Contribution to journalArticlepeer-review

Abstract

As machine learning systems grow in scale, so do their training data requirements, forcing practitioners to automate and outsource the curation of training data in order to achieve state-of-the-art performance. The absence of trustworthy human supervision over the data collection process exposes organizations to security vulnerabilities; training data can be manipulated to control and degrade the downstream behaviors of learned models. The goal of this work is to systematically categorize and discuss a wide range of dataset vulnerabilities and exploits, approaches for defending against these threats, and an array of open problems in this space.

Original languageEnglish (US)
Pages (from-to)1563-1580
Number of pages18
JournalIEEE transactions on pattern analysis and machine intelligence
Volume45
Issue number2
DOIs
StatePublished - Feb 1 2023

Keywords

  • Data poisoning
  • backdoor attacks
  • dataset security

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Applied Mathematics
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics

Fingerprint

Dive into the research topics of 'Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses'. Together they form a unique fingerprint.

Cite this