Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
Authors
Micah Goldblum, Dimitris Tsipras, Chulin Xie, Xinyun Chen, Avi Schwarzschild, Dawn Song, Aleksander Madry, Bo Li, Tom Goldstein
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Abstract
Comprehensive survey systematically categorizing dataset vulnerabilities including poisoning and backdoor attacks, their threat models, and defense mechanisms.
Tags