Cloud Adversarial Example Generation for Remote Sensing Image Classification

TL;DR

This paper introduces a novel cloud-based adversarial attack method for remote sensing images using a Perlin noise generator and differential evolution, achieving high efficiency and transferability in black-box attack scenarios.

Contribution

We propose a Perlin noise-based cloud generation attack utilizing a neural network and differential evolution for efficient black-box adversarial attacks on remote sensing images.

Findings

High attack success rate and query efficiency.

Effective transferability of adversarial examples.

Robustness against adversarial defenses.

Abstract

Most existing adversarial attack methods for remote sensing images merely add adversarial perturbations or patches, resulting in unnatural modifications. Clouds are common atmospheric effects in remote sensing images. Generating clouds on these images can produce adversarial examples better aligning with human perception. In this paper, we propose a Perlin noise based cloud generation attack method. Common Perlin noise based cloud generation is a random, non-optimizable process, which cannot be directly used to attack the target models. We design a Perlin Gradient Generator Network (PGGN), which takes a gradient parameter vector as input and outputs the grids of Perlin noise gradient vectors at different scales. After a series of computations based on the gradient vectors, cloud masks at corresponding scales can be produced. These cloud masks are then weighted and summed depending on a mixing coefficient vector and a scaling factor to produce the final cloud masks. The gradient vector, coefficient vector and scaling factor are collectively represented as a cloud parameter vector, transforming the cloud generation into a black-box optimization problem. The Differential Evolution (DE) algorithm is employed to solve for the optimal solution of the cloud parameter vector, achieving a query-based black-box attack. Detailed experiments confirm that this method has strong attack capabilities and achieves high query efficiency. Additionally, we analyze the transferability of the generated adversarial examples and their robustness in adversarial defense scenarios.