Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning

IEEE Symposium on Security and Privacy, pp. 19-35, 2018.

Cited by: 130|Bibtex|Views123|DOI:https://doi.org/10.1109/SP.2018.00057
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

As machine learning becomes widely used for automated decisions, attackers have strong incentives to manipulate the results and models generated by machine learning algorithms. In this paper, we perform the first systematic study of poisoning attacks and their countermeasures for linear regression models. In poisoning attacks, attackers d...More

Code:

Data:

Your rating :
0

 

Tags
Comments