mlsanityData to 14 Oct 2026

GeoLocator: a location-integrated large multimodal model for inferring geo-privacy

arXiv 2311.13018 ↗First posted 21 Nov 2023cs.CY cs.AI cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Geographic privacy or geo-privacy refers to the keeping private of one's geographic location, especially the restriction of geographical data maintained by personal electronic devices. Geo-privacy is a crucial aspect of personal security; however, it often goes unnoticed in daily activities. With the surge in the use of Large Multimodal Models (LMMs), such as GPT-4, for Open Source Intelligence (OSINT), the potential risks associated with geo-privacy breaches have intensified. This study develops a location-integrated GPT-4 based model named GeoLocator and designs four-dimensional experiments to demonstrate its capability in inferring the locational information of input imageries and/or social media contents. Our experiments reveal that GeoLocator generates specific geographic details with high accuracy and consequently embeds the risk of the model users exposing geospatial information to the public unintentionally, highlighting the thread of online data sharing, information gathering technologies and LLMs on geo-privacy. We conclude with the broader implications of GeoLocator and our findings for individuals and the community at large, by emphasizing the urgency for enhanced awareness and protective measures against geo-privacy leakage in the era of advanced AI and widespread social media usage.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 21 of its 31 references that are in the map. First posted on arXiv 21 Nov 2023.

Builds on

21 of 31 references.

References · 21

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  6. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  7. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 868
  8. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 681
  9. 2023LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understandingcited by 274
  10. 2023K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilizationcited by 69
  11. 2023GPT4GEO: How a Language Model Sees the World's Geographycited by 68
  12. 2023GeoLM: Empowering Language Models for Geospatially Grounded Language Understandingcited by 37
9 more
  1. 2023Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messagescited by 31
  2. 2023Are Large Language Models Geospatially Knowledgeable?cited by 30
  3. 2020More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligencecited by 23
  4. 2023LLM-driven Multimodal Target Volume Contouring in Radiation Oncologycited by 20
  5. 2023Multimodal Machine Learning in Image-Based and Clinical Biomedicine: Survey and Prospectscited by 15
  6. 2023Multimodal Foundation Models for Zero-shot Animal Species Recognition in Camera Trap Imagescited by 13
  7. 2023More Robots are Coming: Large Multimodal Models (ChatGPT) can Solve Visually Diverse Images of Parsons Problemscited by 11
  8. 2023Large Language Models Illuminate a Progressive Pathway to Artificial Healthcare Assistant: A Reviewcited by 8
  9. 2023Evaluating Large Language Models in Ophthalmologycited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 5.

13 papers.

Sort:

By area:

  1. 2025AI Sees Your Location, But With A Bias Toward The Wealthy Worldcited by 14
  2. 2025Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Modelscited by 14
  3. 2025Hyperlocal disaster damage assessment using bi-temporal street-view imagery and pre-trained vision modelscited by 8
  4. 2025Beyond Data Privacy: New Privacy Risks for Large Language Modelscited by 6
  5. 2025GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbationscited by 5
  6. 2025Urban Computing in the Era of Large Language Modelscited by 2
  7. 2025GEO-Detective: Unveiling Location Privacy Risks in Images with LLM Agentscited by 1
  8. 2025Georeferencing complex relative locality descriptions with large language modelscited by 1
  9. 2026Do Vision-Language Models Respect Contextual Integrity in Location Disclosure?cited by 1
  10. 2026RAPID: A Reproducible Multi-Agent Pipeline for Interpretable Disaster Damage Assessment from Satellite and Street-View Imagerycited by 1
  11. 2026Which private attributes do VLMs agree on and predict well?cited by 0
  12. 2026DamageArbiter: A Multimodal Arbitration Framework for Disaster Damage Assessment from Street-View Imagerycited by 0
1 more
  1. 2026Agentic and Generative AI for Open-Source Intelligence and Cyber Investigations: Taxonomy, Evaluation, Challenges, and Future Directionscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Granular Privacy Control for Geolocation with Vision Language Models
  2. 2025Evaluation of Geolocation Capabilities of Multimodal Large Language Models and Analysis of Associated Privacy Risks
  3. 2026Hiding in Plain Sight: A Diffusion-based Mitigation of Geolocation Privacy Leakage in Vision-Language Models
  4. 2025Evaluating Precise Geolocation Inference Capabilities of Vision Language Models
  5. 2026GeoCloak: An Agentic Framework for Semantics-Preserving Geolocation Privacy via Peripheral Clue Manipulation
  6. 2025Toward Reliable VLM: A Fine-Grained Benchmark and Framework for Exposure, Bias, and Inference in Korean Street Views
  7. 2025Assessing the Geolocation Capabilities, Limitations and Societal Risks of Generative Vision-Language Models
  8. 2025Beyond Pixels: Semantic-aware Typographic Attack for Geo-Privacy Protection