mlsanityData to 14 Oct 2026

Through Their Eyes: User Perceptions on Sensitive Attribute Inference of Social Media Videos by Visual Language Models

arXiv 2508.07658 ↗First posted 11 Aug 2025cs.HCcited by 1

On the map: Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness

Abstract (arXiv)

The rapid advancement of Visual Language Models (VLMs) has enabled sophisticated analysis of visual content, leading to concerns about the inference of sensitive user attributes and subsequent privacy risks. While technical capabilities of VLMs are increasingly studied, users' understanding, perceptions, and reactions to these inferences remain less explored, especially concerning videos uploaded on the social media. This paper addresses this gap through a semi-structured interview (N=17), investigating user perspectives on VLM-driven sensitive attribute inference from their visual data. Findings reveal that users perceive VLMs as capable of inferring a range of attributes, including location, demographics, and socioeconomic indicators, often with unsettling accuracy. Key concerns include unauthorized identification, misuse of personal information, pervasive surveillance, and harm from inaccurate inferences. Participants reported employing various mitigation strategies, though with skepticism about their ultimate effectiveness against advanced AI. Users also articulate clear expectations for platforms and regulators, emphasizing the need for enhanced transparency, user control, and proactive privacy safeguards. These insights are crucial for guiding the development of responsible AI systems, effective privacy-enhancing technologies, and informed policymaking that aligns with user expectations and societal values.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 17 of its 66 references that are in the map. First posted on arXiv 11 Aug 2025.

Builds on

17 of 66 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Private Attribute Inference from Images with Vision-Language Models16 Apr

Other references · 16

  1. 2023Beyond Memorization: Violating Privacy Via Inference with Large Language Modelscited by 175
  2. 2023Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendationcited by 114
  3. 2022A Survey on the Fairness of Recommender Systemscited by 102
  4. 2017Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Imagescited by 101
  5. 2017Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Imagescited by 24
  6. 2023Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusioncited by 24
  7. 2022Inferring Sensitive Attributes from Model Explanationscited by 15
  8. 2024User Characteristics in Explainable AI: The Rabbit Hole of Personalization?cited by 12
  9. 2025AiGet: Transforming Everyday Moments into Hidden Knowledge Discovery with AI Assistance on Smart Glassescited by 11
  10. 2018PrivacEye: Privacy-Preserving Head-Mounted Eye Tracking Using Egocentric Scene Image and Eye Movement Featurescited by 8
  11. 2024Adanonymizer: Interactively Navigating and Balancing the Duality of Privacy and Output Performance in Human-LLM Interactioncited by 6
  12. 2025Making AI-Enhanced Videos: Analyzing Generative AI Use Cases in YouTube Content Creationcited by 6
4 more
  1. 2024"Confrontation or Acceptance": Understanding Novice Visual Artists' Perception towards AI-assisted Art Creationcited by 3
  2. 2025Raising Awareness of Location Information Vulnerabilities in Social Media Photos using LLMscited by 2
  3. 2025Evaluating the Efficacy of Large Language Models for Generating Fine-Grained Visual Privacy Policies in Homescited by 1
  4. 2025From Patient Burdens to User Agency: Designing for Real-Time Protection Support in Online Health Consultationscited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Beyond PII: How Users Attempt to Estimate and Mitigate Implicit LLM Inferencecited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025The Pervasive Blind Spot: Benchmarking VLM Inference Risks on Everyday Personal Videos
  2. 2025Assessing Visual Privacy Risks in Multimodal AI: A Novel Taxonomy-Grounded Evaluation of Vision-Language Models
  3. 2024The Phantom Menace: Unmasking Privacy Leakages in Vision-Language Models
  4. 2025Mapping User Trust in Vision Language Models: Research Landscape, Challenges, and Prospects
  5. 2025Who Can See Through You? Adversarial Shielding Against VLM-Based Attribute Inference Attacks
  6. 2026Which private attributes do VLMs agree on and predict well?
  7. 2025MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models
  8. 2024Privacy-Aware Visual Language Models