Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Raising Awareness of Location Information Vulnerabilities in Social Media Photos using LLMs

Ying Ma, Shiquan Zhang, Dongju Yang, Zhanna Sarsenbayeva, Jarrod Knibbe, Jorge Goncalves

TL;DR

This study investigates the privacy risks arising from location information leakage in social media photos due to large language models (LLMs). It introduces an LLM-powered intervention app and assesses its impact through a two-week, in-depth user study with 19 iOS participants, combining quantitative leakage analysis (682 photos analyzed) with qualitative interviews. Key findings show participants were surprised by LLM capabilities, developed intentions to adjust photo-taking/sharing practices, and valued editing features, education, and transparency. The work offers design implications for real-time, user-centered location privacy-preserving technologies that balance visual appeal with privacy and emphasize user autonomy and trust in platforms. Overall, the paper contributes to understanding how to raise awareness and operationalize location privacy protections in the era of powerful AI tools.

Abstract

Location privacy leaks can lead to unauthorised tracking, identity theft, and targeted attacks, compromising personal security and privacy. This study explores LLM-powered location privacy leaks associated with photo sharing on social media, focusing on user awareness, attitudes, and opinions. We developed and introduced an LLM-powered location privacy intervention app to 19 participants, who used it over a two-week period. The app prompted users to reflect on potential privacy leaks that a widely available LLM could easily detect, such as visual landmarks & cues that could reveal their location, and provided ways to conceal this information. Through in-depth interviews, we found that our intervention effectively increased users' awareness of location privacy and the risks posed by LLMs. It also encouraged users to consider the importance of maintaining control over their privacy data and sparked discussions about the future of location privacy-preserving technologies. Based on these insights, we offer design implications to support the development of future user-centred, location privacy-preserving technologies for social media photos.

Raising Awareness of Location Information Vulnerabilities in Social Media Photos using LLMs

TL;DR

This study investigates the privacy risks arising from location information leakage in social media photos due to large language models (LLMs). It introduces an LLM-powered intervention app and assesses its impact through a two-week, in-depth user study with 19 iOS participants, combining quantitative leakage analysis (682 photos analyzed) with qualitative interviews. Key findings show participants were surprised by LLM capabilities, developed intentions to adjust photo-taking/sharing practices, and valued editing features, education, and transparency. The work offers design implications for real-time, user-centered location privacy-preserving technologies that balance visual appeal with privacy and emphasize user autonomy and trust in platforms. Overall, the paper contributes to understanding how to raise awareness and operationalize location privacy protections in the era of powerful AI tools.

Abstract

Location privacy leaks can lead to unauthorised tracking, identity theft, and targeted attacks, compromising personal security and privacy. This study explores LLM-powered location privacy leaks associated with photo sharing on social media, focusing on user awareness, attitudes, and opinions. We developed and introduced an LLM-powered location privacy intervention app to 19 participants, who used it over a two-week period. The app prompted users to reflect on potential privacy leaks that a widely available LLM could easily detect, such as visual landmarks & cues that could reveal their location, and provided ways to conceal this information. Through in-depth interviews, we found that our intervention effectively increased users' awareness of location privacy and the risks posed by LLMs. It also encouraged users to consider the importance of maintaining control over their privacy data and sparked discussions about the future of location privacy-preserving technologies. Based on these insights, we offer design implications to support the development of future user-centred, location privacy-preserving technologies for social media photos.

Paper Structure

This paper contains 40 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Privacy Risks and Awareness in Social Media Platforms
  4. Location Privacy Concerns when Sharing Photos Online
  5. Location Privacy Attacks and Protection Mechanisms
  6. Privacy Attack Methods on SNSs.
  7. Emerging Risks of LLM Applications in Photo Location Privacy.
  8. Mechanisms for Protecting Privacy in Online Photo Sharing.
  9. METHOD
  10. Sampling and Recruitment
  11. User Study Procedure
  12. App framework
  13. Data Collection & Analysis
  14. Ethical Considerations
  15. Findings
  16. ...and 25 more sections

Figures (2)

  • Figure 1: Different features of our application. (a) Analysis phase: where users get information of the location leaks in the photo they uploaded, (b) Edit phase: where users can mask location information, (c) Review phase: where users can verify the final photo and confirm that it no longer contains location leaks.
  • Figure 2: (Left) A photo shared by a participant indicating she is on a mountain landscape; (Right) Detected points of interest and landmarks from this photo. (The participant consented to the use of this photo in the paper.)