GeoLocator: A Location-Integrated Large Multimodal Model (LMM) for Inferring Geo-Privacy
Source abstract
Abstract
To ensure the sustainable development of artificial intelligence (AI) application in urban and geospatial science, it is important to protect the geographic privacy, or geo-privacy, which refers to an individual’s geographic location details. As a crucial aspect of personal security, geo-privacy plays a key role not only in individual protection but also in maintaining ethical standards in geoscientific practices. Despite its importance, geo-privacy is often not sufficiently addressed in daily activities. With the increasing use of large multimodal models (LMMs) such as GPT-4 for open-source intelligence (OSINT), the risks related to geo-privacy breaches have significantly escalated. This study introduces a novel GPT-4-based model, GeoLocator, integrated with location capabilities, and conducts four experiments to evaluate its ability to accurately infer location information from images and social media content. The results demonstrate that GeoLocator can generate specific geographic details with high precision, thereby increasing the potential for inadvertent exposure of sensitive geospatial information. This highlights the dual challenges posed by online data-sharing and information-gathering technologies in the context of geo-privacy. We conclude with a discussion on the broader impacts of GeoLocator and our findings on individuals and communities, emphasizing the urgent need for increased awareness and protective measures against geo-privacy breaches in the era of advancing AI and widespread social media usage. This contribution thus advocates for sustainable and responsible geoscientific practices.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Privacy-Preserving Technologies in Data · Human Mobility and Location-Based Analysis · Privacy, Security, and Data Protection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Spatial Sciences Institute, University of Southern California, Los Angeles, CA 90089, USA
Department of Environmental Health Sciences, University of California—Los Angeles, Los Angeles, CA 90095, USA
References (27)
Show source-provided references
1. More than privacy: Applying differential privacy in key areas of artificial intelligence10.1109/TKDE.2020.3014246 ↗
2. GeoAI: Spatially explicit artificial intelligence techniques for geographic knowledge discovery and beyond10.1080/13658816.2019.1684500 ↗
3. Location privacy-preserving mechanisms in location-based services: A comprehensive survey
4. How to address data privacy concerns when using social media data in conservation science10.1111/cobi.13708 ↗
5. Privacy: History, statistics, policy, laws, preservation and threat analysis
6. Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., and Anadkat, S. (2023). Gpt-4 technical report. arXiv.
7. Attention is all you need
8. Radford, A., Narasimhan, K., Salimans, T., and Sutskever, I. (2018). Improving language understanding by generative pre-training, in progress.
9. Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv.
10. Training language models to follow instructions with human feedback
11. Wang, Y., Mishra, S., Alipoormolabashi, P., Kordi, Y., Mirzaei, A., Arunkumar, A., Ashok, A., Dhanasekaran, A.S., Naik, A., and Stap, D. (2022). Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks. arXiv.10.18653/v1/2022.emnlp-main.340 ↗
12. OpenAi (2023, December 19). ChatGPT. Available online: https://openai.com/chatgpt.
13. Holmes, J., Ye, S., Li, Y., Wu, S.-N., Liu, Z., Wu, Z., Zhao, H., Jiang, X., Liu, W., and Wei, H. (2023). Evaluating Large Language Models in Ophthalmology. arXiv.
14. Yuan, M., Bao, P., Yuan, J., Shen, Y., Chen, Z., Xie, Y., Zhao, J., Chen, Y., Zhang, L., and Shen, L. (2023). Large Language Models Illuminate a Progressive Pathway to Artificial Healthcare Assistant: A Review. arXiv.10.1016/j.medp.2024.100030 ↗
15. Hou, I., Man, O., Mettille, S., Gutierrez, S., Angelikas, K., and MacNeil, S. (2023). More Robots are Coming: Large Multimodal Models (ChatGPT) can Solve Visually Diverse Images of Parsons Problems. arXiv.10.1145/3636243.3636247 ↗
16. Liu, H., Li, C., Wu, Q., and Lee, Y.J. (2023). Visual Instruction Tuning. arXiv.
17. Zhu, D., Chen, J., Shen, X., Li, X., and Elhoseiny, M. (2023). MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. arXiv.
18. Zhang, Y., Zhang, R., Gu, J., Zhou, Y., Lipka, N., Yang, D., and Sun, T. (2023). LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding. arXiv.
19. Fabian, Z., Miao, Z., Li, C., Zhang, Y., Liu, Z., Hernández, A., Montes-Rojas, A., Escucha, R., Siabatto, L., and Link, A. (2023). Multimodal Foundation Models for Zero-shot Animal Species Recognition in Camera Trap Images. arXiv.
20. Picard, C., Edwards, K.M., Doris, A.C., Man, B., Giannone, G., Alam, M.F., and Ahmed, F. (2023). From Concept to Manufacturing: Evaluating Vision-Language Models for Engineering Design. arXiv.10.12968/S2514-9768(23)90393-5 ↗
21. Oh, Y., Park, S., Byun, H.K., Kim, J.S., and Ye, J.C. (2023). LLM-driven Multimodal Target Volume Contouring in Radiation Oncology. arXiv.
22. Yang, Z., Li, L., Lin, K., Wang, J., Lin, C.-C., Liu, Z., and Wang, L. (2023). The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision). arXiv.
23. Roberts, J., Lüddecke, T., Das, S., Han, K., and Albanie, S. (2023). GPT4GEO: How a Language Model Sees the World’s Geography. arXiv.
24. Deng, C., Zhang, T., He, Z., Xu, Y., Chen, Q., Shi, Y., Xu, Y., Fu, L., Zhang, W., and Wang, X. (2023). K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization. arXiv.10.1145/3616855.3635772 ↗
25. Li, Z., Zhou, W., Chiang, Y.-Y., and Chen, M. (2023). GeoLM: Empowering Language Models for Geospatially Grounded Language Understanding. arXiv.10.18653/v1/2023.emnlp-main.317 ↗
26. Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages10.1080/13658816.2023.2266495 ↗
27. Bhandari, P., Anastasopoulos, A., and Pfoser, D. (2023). Are Large Language Models Geospatially Knowledgeable?. arXiv.10.1145/3589132.3625625 ↗