Block Switching: A Stochastic Approach for Deep Learning Security

by   Xiao Wang, et al.

Recent study of adversarial attacks has revealed the vulnerability of modern deep learning models. That is, subtly crafted perturbations of the input can make a trained network with high accuracy produce arbitrary incorrect predictions, while maintain imperceptible to human vision system. In this paper, we introduce Block Switching (BS), a defense strategy against adversarial attacks based on stochasticity. BS replaces a block of model layers with multiple parallel channels, and the active channel is randomly assigned in the run time hence unpredictable to the adversary. We show empirically that BS leads to a more dispersed input gradient distribution and superior defense effectiveness compared with other stochastic defenses such as stochastic activation pruning (SAP). Compared to other defenses, BS is also characterized by the following features: (i) BS causes less test accuracy drop; (ii) BS is attack-independent and (iii) BS is compatible with other defenses and can be used jointly with others.


page 1

page 2

page 3

page 4


Protecting Neural Networks with Hierarchical Random Switching: Towards Better Robustness-Accuracy Trade-off for Stochastic Defenses

Despite achieving remarkable success in various domains, recent studies ...

A critique of the DeepSec Platform for Security Analysis of Deep Learning Models

At IEEE S&P 2019, the paper "DeepSec: A Uniform Platform for Security An...

An integrated Auto Encoder-Block Switching defense approach to prevent adversarial attacks

According to recent studies, the vulnerability of state-of-the-art Neura...

Adversarial Attacks against Deep Learning Based Power Control in Wireless Communications

We consider adversarial machine learning based attacks on power allocati...

Game Theory for Adversarial Attacks and Defenses

Adversarial attacks can generate adversarial inputs by applying small bu...

Towards Effective and Robust Neural Trojan Defenses via Input Filtering

Trojan attacks on deep neural networks are both dangerous and surreptiti...

Poisons that are learned faster are more effective

Imperceptible poisoning attacks on entire datasets have recently been to...