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

arXiv: https://arxiv.org/abs/2508.07658 · HTML: https://mlsanity.com/paper/2508.07658/

## Key facts

- Cited by 1 papers 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.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)

## Builds on (most cited first, 17 of 17)

- [Beyond Memorization: Violating Privacy Via Inference with Large Language Models](https://mlsanity.com/paper/2310.07298/) (2023)
- [Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendation](https://mlsanity.com/paper/2305.07609/) (2023)
- [A Survey on the Fairness of Recommender Systems](https://mlsanity.com/paper/2206.03761/) (2022)
- [Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images](https://mlsanity.com/paper/1703.10660/) (2017)
- [Private Attribute Inference from Images with Vision-Language Models](https://mlsanity.com/paper/2404.10618/) (2024)
- [Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Images](https://mlsanity.com/paper/1712.01066/) (2017)
- [Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion](https://mlsanity.com/paper/2312.10692/) (2023)
- [Inferring Sensitive Attributes from Model Explanations](https://mlsanity.com/paper/2208.09967/) (2022)
- [User Characteristics in Explainable AI: The Rabbit Hole of Personalization?](https://mlsanity.com/paper/2403.00137/) (2024)
- [AiGet: Transforming Everyday Moments into Hidden Knowledge Discovery with AI Assistance on Smart Glasses](https://mlsanity.com/paper/2501.16240/) (2025)
- [PrivacEye: Privacy-Preserving Head-Mounted Eye Tracking Using Egocentric Scene Image and Eye Movement Features](https://mlsanity.com/paper/1801.04457/) (2018)
- [Adanonymizer: Interactively Navigating and Balancing the Duality of Privacy and Output Performance in Human-LLM Interaction](https://mlsanity.com/paper/2410.15044/) (2024)
- [Making AI-Enhanced Videos: Analyzing Generative AI Use Cases in YouTube Content Creation](https://mlsanity.com/paper/2503.03134/) (2025)
- ["Confrontation or Acceptance": Understanding Novice Visual Artists' Perception towards AI-assisted Art Creation](https://mlsanity.com/paper/2410.14925/) (2024)
- [Raising Awareness of Location Information Vulnerabilities in Social Media Photos using LLMs](https://mlsanity.com/paper/2503.20226/) (2025)
- [Evaluating the Efficacy of Large Language Models for Generating Fine-Grained Visual Privacy Policies in Homes](https://mlsanity.com/paper/2508.00321/) (2025)
- [From Patient Burdens to User Agency: Designing for Real-Time Protection Support in Online Health Consultations](https://mlsanity.com/paper/2508.00328/) (2025)

## Built on by (most cited first, 1 of 1)

- [Beyond PII: How Users Attempt to Estimate and Mitigate Implicit LLM Inference](https://mlsanity.com/paper/2509.12152/) (2025)

## 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.