Feature selection

Elastic net regularization

Feature (linguistics)

Mathematics

Gene

Data mining

World Wide Web

Machine learning

Mathematical analysis

Philosophy

Random forest

Artificial intelligence

Generalization

Chemistry

Lasso (programming language)

Computer science

Linguistics

Malware

Adversarial system

Computer security

Training set

Biochemistry

Robustness (evolution)

arXiv (Cornell University)

Learning in adversarial settings is becoming an important task for application domains where attackers may inject malicious data into the training set to subvert normal operation of data-driven technologies. Feature selection has been widely used in machine learning for security applications to improve generalization and computational efficiency, although it is not clear whether its use may be beneficial or even counterproductive when training data are poisoned by intelligent attackers. In this work, we shed light on this issue by providing a framework to investigate the robustness of popular feature selection methods, including LASSO, ridge regression and the elastic net. Our results on malware detection show that feature selection methods can be significantly compromised under attack (we can reduce LASSO to almost random choices of feature sets by careful insertion of less than 5% poisoned training samples), highlighting the need for specific countermeasures.

Is feature selection secure against training data poisoning?