EFSAttack: Edge Noise-Constrained Black-Box Attack Using Artificial Fish Swarm Algorithm
Open Access
- 21 June 2024
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 13 (13) , 2446
Abstract
Black-box attacks generate adversarial examples by querying the target model and updating the noise according to the feedback. However, the current black-box attack methods require excessive queries to generate adversarial examples, increasing the risk of detection by target defense systems. Furthermore, the current black-box attack methods primarily focus on controlling the magnitude of perturbations while neglecting the impact of perturbation placement on the stealthiness of adversarial examples. To this end, we propose a novel edge noise-constrained black-box attack method using the artificial fish swarm algorithm (EFSAttack). EFSAttack introduces the concept of edge noise constraint to indicate the low-frequency region of the image where perturbations are added and employs edge noise constraint to improve the population initialization and population evolution process. The experiments on CIFAR-10 and MNIST show notable improvements in the success rates, query efficiency, and adversarial example invisibility.Keywords
This publication has 19 references indexed in Scilit:
- A Survey on Evaluation of Large Language ModelsACM Transactions on Intelligent Systems and Technology, 2024
- MedMNIST v2 - A large-scale lightweight benchmark for 2D and 3D biomedical image classificationScientific Data, 2023
- A review of artificial fish swarm algorithms: recent advances and applicationsArtificial Intelligence Review, 2022
- ABCAttack: A Gradient-Free Optimization Black-Box Attack for Fooling Deep Image ClassifiersEntropy, 2022
- A Distributed Black-Box Adversarial Attack Based on Multi-Group Particle Swarm OptimizationSensors, 2020
- One Pixel Attack for Fooling Deep Neural NetworksIEEE Transactions on Evolutionary Computation, 2019
- Artificial fish swarm algorithm: a survey of the state-of-the-art, hybridization, combinatorial and indicative applicationsArtificial Intelligence Review, 2012
- Ant colony optimizationIEEE Computational Intelligence Magazine, 2006
- A Computational Approach to Edge DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1986
- Optimization by Simulated AnnealingScience, 1983