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

2022 article goldblum2022dataset ○ Not yet verified

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.

BibTeX

Local Entry

@article{goldblum2022dataset,
  title = {Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses},
  author = {Micah Goldblum and Dimitris Tsipras and Chulin Xie and Xinyun Chen and Avi Schwarzschild and Dawn Song and Aleksander Madry and Bo Li and Tom Goldstein},
  year = {2022},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  url = {https://arxiv.org/abs/2012.10544},
  abstract = {Comprehensive survey systematically categorizing dataset vulnerabilities including poisoning and backdoor attacks, their threat models, and defense mechanisms.}
}

From OPENALEX

@article{goldblum2022dataset,
  title = {Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses},
  author = {Micah Goldblum and Dimitris Tsipras and Chulin Xie and Xinyun Chen and Avi Schwarzschild and Dawn Song and Aleksander Mądry and Bo Li and Tom Goldstein},
  year = {2022},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  doi = {10.1109/tpami.2022.3162397}
}