Enhancing robustness of machine learning systems via data transformations
Authors:
- 1 March 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
We propose the use of data transformations as a defense against evasion attacks on ML classifiers. We present and investigate strategies for incorporating a variety of data transformations including dimensionality reduction via Principal Component Analysis to enhance the resilience of machine learning, targeting both the classification and the training phase. We empirically evaluate and demonstrate the feasibility of linear transformations of data as a defense mechanism against evasion attacks using multiple real-world datasets. Our key findings are that the defense is (i) effective against the best known evasion attacks from the literature, resulting in a two-fold increase in the resources required by a white-box adversary with knowledge of the defense for a successful attack, (ii) applicable across a range of ML classifiers, including Support Vector Machines and Deep Neural Networks, and (iii) generalizable to multiple application domains, including image classification and human activity classification.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Towards Evaluating the Robustness of Neural Networks2017
- The Limitations of Deep Learning in Adversarial Settings2016
- Deep neural networks are easily fooled: High confidence predictions for unrecognizable images2015
- Evasion Attacks against Machine Learning at Test Time2013
- Adversarial machine learning2011
- A framework for quantitative security analysis of machine learning2009
- Can machine learning be secure?2006