Poisoning Attacks against Support Vector Machines

2012 inproceedings biggio2012poisoning ○ Not yet verified

Authors

Battista Biggio, Blaine Nelson, Pavel Laskov

Venue

Proceedings of the 29th International Conference on Machine Learning (ICML)

Abstract

Investigates poisoning attacks against SVMs where adversaries inject crafted training data to increase test error. Uses gradient ascent to construct malicious data points.

BibTeX

Local Entry

@inproceedings{biggio2012poisoning,
  title = {Poisoning Attacks against Support Vector Machines},
  author = {Battista Biggio and Blaine Nelson and Pavel Laskov},
  year = {2012},
  booktitle = {Proceedings of the 29th International Conference on Machine Learning (ICML)},
  url = {https://arxiv.org/abs/1206.6389},
  abstract = {Investigates poisoning attacks against SVMs where adversaries inject crafted training data to increase test error. Uses gradient ascent to construct malicious data points.}
}

From OPENALEX

@inproceedings{biggio2012poisoning,
  title = {Poisoning Attacks against Support Vector Machines},
  author = {Battista Biggio and Blaine Nelson and Pavel Laskov},
  year = {2012},
  booktitle = {arXiv (Cornell University)},
  doi = {10.48550/arxiv.1206.6389}
}