Universal Adversarial Examples in Remote Sensing: Methodology and Benchmark

TL;DR

This paper introduces a novel black-box attack method for remote sensing neural networks, demonstrating high transferability of universal adversarial examples and providing a benchmark dataset for future robustness research.

Contribution

The study proposes Mixup-Attack and Mixcut-Attack methods for generating transferable adversarial examples in remote sensing, and releases the UAE-RS dataset for benchmarking defenses.

Findings

High success rates in fooling state-of-the-art models

Universal adversarial examples transfer across different networks

UAE-RS dataset enables robustness evaluation

Abstract

Deep neural networks have achieved great success in many important remote sensing tasks. Nevertheless, their vulnerability to adversarial examples should not be neglected. In this study, we systematically analyze the universal adversarial examples in remote sensing data for the first time, without any knowledge from the victim model. Specifically, we propose a novel black-box adversarial attack method, namely Mixup-Attack, and its simple variant Mixcut-Attack, for remote sensing data. The key idea of the proposed methods is to find common vulnerabilities among different networks by attacking the features in the shallow layer of a given surrogate model. Despite their simplicity, the proposed methods can generate transferable adversarial examples that deceive most of the state-of-the-art deep neural networks in both scene classification and semantic segmentation tasks with high success rates. We further provide the generated universal adversarial examples in the dataset named UAE-RS, which is the first dataset that provides black-box adversarial samples in the remote sensing field. We hope UAE-RS may serve as a benchmark that helps researchers to design deep neural networks with strong resistance toward adversarial attacks in the remote sensing field. Codes and the UAE-RS dataset are available online (https://github.com/YonghaoXu/UAE-RS).