Nothing Special   »   [go: up one dir, main page]
Search
 
loader loading subjects...
cover
Adversarial Label Flips Attack on Support Vector Machines
Han Xiao, Huang Xiao, Claudia Eckert
870 - 875
10.3233/978-1-61499-098-7-870
Frontiers in Artificial Intelligence and Applications
Volume 242: ECAI 2012
Abstract

To develop a robust classification algorithm in the adversarial setting, it is important to understand the adversary's strategy. We address the problem of label flips attack where an adversary contaminates the training set through flipping labels. By analyzing the objective of the adversary, we formulate an optimization framework for finding the label flips that maximize the classification error. An algorithm for attacking support vector machines is derived. Experiments demonstrate that the accuracy of classifiers is significantly degraded under the attack.

Download
Creative Commons License