DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples

TL;DR

DeepCloak is a defense mechanism that enhances neural network robustness by removing unnecessary features, thereby limiting adversarial attack capabilities and improving resistance against maliciously-perturbed inputs.

Contribution

This paper introduces DeepCloak, a novel, easy-to-implement method that improves DNN robustness by feature pruning, reducing vulnerability to adversarial samples.

Findings

DeepCloak increases model robustness against adversarial samples.

It is computationally efficient compared to other defenses.

Experimental results show improved accuracy on adversarial inputs.

Abstract

Recent studies have shown that deep neural networks (DNN) are vulnerable to adversarial samples: maliciously-perturbed samples crafted to yield incorrect model outputs. Such attacks can severely undermine DNN systems, particularly in security-sensitive settings. It was observed that an adversary could easily generate adversarial samples by making a small perturbation on irrelevant feature dimensions that are unnecessary for the current classification task. To overcome this problem, we introduce a defensive mechanism called DeepCloak. By identifying and removing unnecessary features in a DNN model, DeepCloak limits the capacity an attacker can use generating adversarial samples and therefore increase the robustness against such inputs. Comparing with other defensive approaches, DeepCloak is easy to implement and computationally efficient. Experimental results show that DeepCloak can increase the performance of state-of-the-art DNN models against adversarial samples.