A Black-box Attack on Neural Networks Based on Swarm Evolutionary Algorithm

by   Xiaolei Liu, et al.

Neural networks play an increasingly important role in the field of machine learning and are included in many applications in society. Unfortunately, neural networks suffer from adversarial samples generated to attack them. However, most of the generation approaches either assume that the attacker has full knowledge of the neural network model or are limited by the type of attacked model. In this paper, we propose a new approach that generates a black-box attack to neural networks based on the swarm evolutionary algorithm. Benefiting from the improvements in the technology and theoretical characteristics of evolutionary algorithms, our approach has the advantages of effectiveness, black-box attack, generality, and randomness. Our experimental results show that both the MNIST images and the CIFAR-10 images can be perturbed to successful generate a black-box attack with 100% probability on average. In addition, the proposed attack, which is successful on distilled neural networks with almost 100% probability, is resistant to defensive distillation. The experimental results also indicate that the robustness of the artificial intelligence algorithm is related to the complexity of the model and the data set. In addition, we find that the adversarial samples to some extent reproduce the characteristics of the sample data learned by the neural network model.


page 4

page 5

page 8

page 9


Enhanced Attacks on Defensively Distilled Deep Neural Networks

Deep neural networks (DNNs) have achieved tremendous success in many tas...

Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization

Fooling deep neural networks (DNNs) with the black-box optimization has ...

PICA: A Pixel Correlation-based Attentional Black-box Adversarial Attack

The studies on black-box adversarial attacks have become increasingly pr...

A Melting Pot of Evolution and Learning

We survey eight recent works by our group, involving the successful blen...

Neural Modelling of Dynamic Systems with Time Delays Based on an Adjusted NEAT Algorithm

A problem related to the development of an algorithm designed to find an...

Few-Features Attack to Fool Machine Learning Models through Mask-Based GAN

GAN is a deep-learning based generative approach to generate contents su...

Interpretability of Neural Network With Physiological Mechanisms

Deep learning continues to play as a powerful state-of-art technique tha...

Please sign up or login with your details

Forgot password? Click here to reset