# What Your Posts Reveal: A Benchmark and Agentic Framework for User-Level Privacy Leakage on Social Media

arXiv: https://arxiv.org/abs/2606.06784 · HTML: https://mlsanity.com/paper/2606.06784/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 44 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval](https://mlsanity.com/paper/2004.01804/) (2020)
- [Automated Annotation with Generative AI Requires Validation](https://mlsanity.com/paper/2306.00176/) (2023)
- [PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing](https://mlsanity.com/paper/2601.21957/) (2026)
- [Private Attribute Inference from Images with Vision-Language Models](https://mlsanity.com/paper/2404.10618/) (2024)
- [Measuring and Reducing LLM Hallucination without Gold-Standard Answers](https://mlsanity.com/paper/2402.10412/) (2024)
- [Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models](https://mlsanity.com/paper/2506.14674/) (2025)
- [Privacy in Social Media: Identification, Mitigation and Applications](https://mlsanity.com/paper/1808.02191/) (2018)
- [Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond](https://mlsanity.com/paper/2408.11338/) (2024)
- [Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search](https://mlsanity.com/paper/2502.04951/) (2025)
- [Large-scale online deanonymization with LLMs](https://mlsanity.com/paper/2602.16800/) (2026)
- [Automated Profile Inference with Language Model Agents](https://mlsanity.com/paper/2505.12402/) (2025)
- [The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework](https://mlsanity.com/paper/2505.19139/) (2025)
- [Auditing Data Membership in Reinforcement Learning With Verifiable Rewards](https://mlsanity.com/paper/2511.14045/) (2025)
- [Assessing Visual Privacy Risks in Multimodal AI: A Novel Taxonomy-Grounded Evaluation of Vision-Language Models](https://mlsanity.com/paper/2509.23827/) (2025)
- [GasAgent: A Multi-Agent Framework for Automated Gas Optimization in Smart Contracts](https://mlsanity.com/paper/2507.15761/) (2025)
- [Client-side Gradient Inversion Against Federated Learning from Poisoning](https://mlsanity.com/paper/2309.07415/) (2023)
- [Protecting Vulnerable Voices: Synthetic Dataset Generation for Self-Disclosure Detection](https://mlsanity.com/paper/2507.22930/) (2025)
- [PII-VisBench: Evaluating Personally Identifiable Information Safety in Vision Language Models Along a Continuum of Visibility](https://mlsanity.com/paper/2601.05739/) (2026)
- [Please Forget Where I Was Last Summer: The Privacy Risks of Public Location (Meta)Data](https://mlsanity.com/paper/1901.00897/) (2019)
- [CHASM: Unveiling Covert Advertisements on Chinese Social Media](https://mlsanity.com/paper/2604.20511/) (2026)
- [TxSum: User-Centered Ethereum Transaction Understanding with Micro-Level Semantic Grounding](https://mlsanity.com/paper/2512.06933/) (2025)

## Built on by (most cited first, 2 of 2)

- [AccretionLink: On-Device Auditing of Exposure-Control Attacks on Attribute Inference](https://mlsanity.com/paper/2608.14735/) (2026)
- [TransMeme: A Multi-Agent Framework for Cross-Cultural Meme Transcreation](https://mlsanity.com/paper/2608.27127/) (2026)

## Abstract (arXiv)

Public social media posts can reveal private information through weak cues scattered across text, images, or metadata. Such leakage is often cumulative and cross-post: cues that appear harmless in isolation may jointly expose a user's home, workplace, or routine. However, current research lacks a unified benchmark for user-level multimodal privacy leakage and an evaluation metric that captures exposure severity beyond binary accuracy. To address these gaps, we propose SopriBench, a synthetic benchmark guided by leakage patterns abstracted from a private reference corpus of Rednote and Instagram accounts, covering 50 user profiles and 1,569 images with attributes, contextual sensitivity, granularity, leakage type, inference difficulty, and supporting evidence. We further introduce the Privacy Exposure Score (PES), which weights value granularity by contextual sensitivity. Inspired by abductive reasoning, we introduce Argus, a training-free agentic framework for cumulative leakage inference. Argus forms hypotheses from accumulated evidence, verifies supporting evidence, and aggregates cross-post cues into privacy profiles, achieving 0.55 PES, a 25% improvement over the strongest baseline, with the largest gain on cross-post leakage.