POBA-GA: Perturbation Optimized Black-Box Adversarial Attacks via Genetic Algorithm

Abstract

Most deep learning models are easily vulnerable to adversarial attacks. Various adversarial attacks are designed to evaluate the robustness of models and develop defense model. Currently, adversarial attacks are brought up to attack their own target model with their own evaluation metrics. And most of the black-box adversarial attack algorithms cannot achieve the expected success rate compared with white-box attacks. In this paper, comprehensive evaluation metrics are brought up for different adversarial attack methods. A novel perturbation optimized black-box adversarial attack based on genetic algorithm (POBA-GA) is proposed for achieving white-box comparable attack performances. Approximate optimal adversarial examples are evolved through evolutionary operations including initialization, selection, crossover and mutation. Fitness function is specifically designed to evaluate the example individual in both aspects of attack ability and perturbation control. Population diversity strategy is brought up in evolutionary process to promise the approximate optimal perturbations obtained. Comprehensive experiments are carried out to testify POBA-GA's performances. Both simulation and application results prove that our method is better than current state-of-art black-box attack methods in aspects of attack capability and perturbation control.

References in corpus (16)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• A Survey on Deep Learning in Medical Image Analysis
• How transferable are features in deep neural networks?
• Brain Tumor Segmentation with Deep Neural Networks
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• Roulette-wheel selection via stochastic acceptance
• Robust Physical-World Attacks on Deep Learning Models
• Black-box Adversarial Attacks with Limited Queries and Information
• Understanding Measures of Uncertainty for Adversarial Example Detection
• Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
• Houdini: Fooling Deep Structured Prediction Models
• Black-Box Attacks against RNN based Malware Detection Algorithms
• UPSET and ANGRI : Breaking High Performance Image Classifiers
• Data Driven Exploratory Attacks on Black Box Classifiers in Adversarial Domains
• Evaluation of Momentum Diverse Input Iterative Fast Gradient Sign Method (M-DI2-FGSM) Based Attack Method on MCS 2018 Adversarial Attacks on Black Box Face Recognition System
• ASP:A Fast Adversarial Attack Example Generation Framework based on Adversarial Saliency Prediction

Cited by in corpus (6)

• Adversarial Machine Learning in Image Classification: A Survey Towards the Defender's Perspective
• Vulnerability of deep neural networks for detecting COVID-19 cases from chest X-ray images to universal adversarial attacks
• A Survey of Black-Box Adversarial Attacks on Computer Vision Models
• Black-box adversarial attacks using Evolution Strategies
• Simple black-box universal adversarial attacks on medical image classification based on deep neural networks
• Qualities, challenges and future of genetic algorithms: a literature review