Building Privacy-Preserving and Secure Geospatial Artificial Intelligence Foundation Models

Abstract

In recent years we have seen substantial advances in foundation models for artificial intelligence, including language, vision, and multimodal models. Recent studies have highlighted the potential of using foundation models in geospatial artificial intelligence, known as GeoAI Foundation Models, for geographic question answering, remote sensing image understanding, map generation, and location-based services, among others. However, the development and application of GeoAI foundation models can pose serious privacy and security risks, which have not been fully discussed or addressed to date. This paper introduces the potential privacy and security risks throughout the lifecycle of GeoAI foundation models and proposes a comprehensive blueprint for research directions and preventative and control strategies. Through this vision paper, we hope to draw the attention of researchers and policymakers in geospatial domains to these privacy and security risks inherent in GeoAI foundation models and advocate for the development of privacy-preserving and secure GeoAI foundation models.

1 figure

References in corpus (16)

• LLaMA: Open and Efficient Foundation Language Models
• Language Models are Few-Shot Learners
• Evaluating Large Language Models Trained on Code
• Segment Anything
• Toolformer: Language Models Can Teach Themselves to Use Tools
• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
• Ignore Previous Prompt: Attack Techniques For Language Models
• On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence
• LSTM-TrajGAN: A Deep Learning Approach to Trajectory Privacy Protection
• BadGPT: Exploring Security Vulnerabilities of ChatGPT via Backdoor Attacks to InstructGPT
• CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations
• ImageBind: One Embedding Space To Bind Them All
• Philosophical Foundations of GeoAI: Exploring Sustainability, Diversity, and Bias in GeoAI and Spatial Data Science
• Autonomous GIS: the next-generation AI-powered GIS
• Bag of Tricks for Training Data Extraction from Language Models
• CATS: Conditional Adversarial Trajectory Synthesis for Privacy-Preserving Trajectory Data Publication Using Deep Learning Approaches