Shared References

← Back to browse

Tag: security (1 references)

Poisoning Attacks against Support Vector Machines 2012 inproceedings

Battista Biggio, Blaine Nelson, Pavel Laskov

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

data-poisoningadversarial-mlsecuritysvm
View details Source Proceedings of the 29th International Conference on Machine Learning (ICML)