Defending Malware Classification Networks Against Adversarial Perturbations with Non-Negative Weight Restrictions

Understand

There is a growing body of literature showing that deep neural networks are vulnerable to adversarial input modification.

• Recently this work has been extended from image classification to malware classification over boolean features.
• In this paper we present several new methods for training restricted networks in this specific domain that are highly effective at preventing adversarial perturbations.
• We start with a fully adversarially resistant neural network that has hard non-negative weight restrictions and is equivalent to learning a monotonic boolean function and then attempt to relax the constraints to improve classifier accuracy.