AI Security for Geoscience and Remote Sensing: Challenges and Future Trends

Abstract

Recent advances in artificial intelligence (AI) have significantly intensified research in the geoscience and remote sensing (RS) field. AI algorithms, especially deep learning-based ones, have been developed and applied widely to RS data analysis. The successful application of AI covers almost all aspects of Earth observation (EO) missions, from low-level vision tasks like super-resolution, denoising and inpainting, to high-level vision tasks like scene classification, object detection and semantic segmentation. While AI techniques enable researchers to observe and understand the Earth more accurately, the vulnerability and uncertainty of AI models deserve further attention, considering that many geoscience and RS tasks are highly safety-critical. This paper reviews the current development of AI security in the geoscience and RS field, covering the following five important aspects: adversarial attack, backdoor attack, federated learning, uncertainty and explainability. Moreover, the potential opportunities and trends are discussed to provide insights for future research. To the best of the authors' knowledge, this paper is the first attempt to provide a systematic review of AI security-related research in the geoscience and RS community. Available code and datasets are also listed in the paper to move this vibrant field of research forward.

References in corpus (36)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• Federated Learning: Challenges, Methods, and Future Directions
• Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
• Deep learning in remote sensing: a review
• Remote Sensing Image Scene Classification: Benchmark and State of the Art
• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges
• Recent Advances in Domain Adaptation for the Classification of Remote Sensing Data
• Exploring Models and Data for Remote Sensing Image Caption Generation
• Evidential Deep Learning to Quantify Classification Uncertainty
• Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey
• Predictive Uncertainty Estimation via Prior Networks
• RSVQA: Visual Question Answering for Remote Sensing Data
• Is feature selection secure against training data poisoning?
• Februus: Input Purification Defense Against Trojan Attacks on Deep Neural Network Systems
• Neural Trojans
• A Survey of Uncertainty in Deep Neural Networks
• Unsupervised Domain Adaptation using Generative Adversarial Networks for Semantic Segmentation of Aerial Images
• On Empirical Comparisons of Optimizers for Deep Learning
• SEN12MS-CR-TS: A Remote Sensing Data Set for Multi-modal Multi-temporal Cloud Removal
• Evaluating explainable artificial intelligence methods for multi-label deep learning classification tasks in remote sensing
• Universal Adversarial Examples in Remote Sensing: Methodology and Benchmark
• Towards a Collective Agenda on AI for Earth Science Data Analysis
• Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defense
• Stop-and-Go: Exploring Backdoor Attacks on Deep Reinforcement Learning-based Traffic Congestion Control Systems
• Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks
• Threatening Patch Attacks on Object Detection in Optical Remote Sensing Images
• Adversarial Example in Remote Sensing Image Recognition
• Qualitative Analysis of Monte Carlo Dropout
• Inhibited Softmax for Uncertainty Estimation in Neural Networks
• Backdoor Attacks for Remote Sensing Data with Wavelet Transform
• Evaluating Uncertainty Estimation Methods on 3D Semantic Segmentation of Point Clouds

Cited by in corpus (7)

• C2F-SemiCD: A Coarse-to-Fine Semi-Supervised Change Detection Method Based on Consistency Regularization in High-Resolution Remote Sensing Images
• Diffusion Models Meet Remote Sensing: Principles, Methods, and Perspectives
• Threatening Patch Attacks on Object Detection in Optical Remote Sensing Images
• Towards Assessing the Synthetic-to-Measured Adversarial Vulnerability of SAR ATR
• Quantitative Analysis of Primary Attribution Explainable Artificial Intelligence Methods for Remote Sensing Image Classification
• On the Adversarial Vulnerabilities of Transfer Learning in Remote Sensing
• Elevator, Escalator, or Neither? Classifying Conveyor State Using Smartphone under Arbitrary Pedestrian Behavior