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

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 org...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 2; pp. 1563 - 1580
Main Authors: Goldblum, Micah, Tsipras, Dimitris, Xie, Chulin, Chen, Xinyun, Schwarzschild, Avi, Song, Dawn, Madry, Aleksander, Li, Bo, Goldstein, Tom
Format: Journal Article
Language:English
Published: United States IEEE 01.02.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
backdoor attacks
Data collection
Data models
Data poisoning
dataset security
Datasets
Machine learning
Security
Servers
Toxicology
Training
Training data
Unsolicited e-mail
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2022.3162397