Back to Search Start Over

Adversarial Edit Attacks for Tree Data

Authors :
Paaßen, Benjamin
Yin, Hujun
Camacho, David
Tino, Peter
Source :
Intelligent Data Engineering and Automated Learning – IDEAL 2019 ISBN: 9783030336066, IDEAL (1)
Publication Year :
2019
Publisher :
Springer International Publishing, 2019.

Abstract

Many machine learning models can be attacked with adversarial examples, i.e. inputs close to correctly classified examples that are classified incorrectly. However, most research on adversarial attacks to date is limited to vectorial data, in particular image data. In this contribution, we extend the field by introducing adversarial edit attacks for tree-structured data with potential applications in medicine and automated program analysis. Our approach solely relies on the tree edit distance and a logarithmic number of black-box queries to the attacked classifier without any need for gradient information. We evaluate our approach on two programming and two biomedical data sets and show that many established tree classifiers, like tree-kernel-SVMs and recursive neural networks, can be attacked effectively.<br />accepted at the 20th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL)

Details

ISBN :
978-3-030-33606-6
ISBNs :
9783030336066
Database :
OpenAIRE
Journal :
Intelligent Data Engineering and Automated Learning – IDEAL 2019 ISBN: 9783030336066, IDEAL (1)
Accession number :
edsair.doi.dedup.....99d4baa48a0b7745253af66320923a0d