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

• URL: http://arxiv.org/abs/2606.06784v1
• Date: Fri, 05 Jun 2026 00:02:47 GMT
• Title: What Your Posts Reveal: A Benchmark and Agentic Framework for User-Level Privacy Leakage on Social Media
• Abstract summary: Public social media posts can reveal private information through weak cues scattered across text, images, or metadata.<n>We propose SopriBench, a synthetic benchmark guided by leakage patterns abstracted from a private reference corpus of Rednote and Instagram accounts.<n>Inspired by abductive reasoning, we introduce Argus, a training-free agentic framework for cumulative leakage inference.
• Score: 14.75272852371927
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Privacy-Aware Synthetic Video Benchmarking and Relational Evaluation for Worker-Under-Suspended-Load Detection [46.13517417540154]
  We introduce SynthSite, a focused synthetic video benchmark of 55 clips spanning varied load configurations, viewpoints, clutter, and surveillance conditions.<n>We ask whether worker appearance can be suppressed without undermining downstream hazard recognition.<n>We find that structure-hugging obfuscations retain substantially more downstream utility than appearance-smoothing baselines.
  arXiv  Detail & Related papers  (2026-07-17T06:20:20Z)
• Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs [61.15237978606501]
  Large language models can infer private user attributes from user-generated text.<n>Existing anonymization-based defenses are coarse-grained, lacking word-level precision in anonymizing privacy-leaking elements.<n>We propose a unified defense framework that combines fine-grained anonymization (TRACE) with inference-preventing optimization (RPS)
  arXiv  Detail & Related papers  (2026-02-12T03:37:50Z)
• CanaryBench: Stress Testing Privacy Leakage in Cluster-Level Conversation Summaries [0.0]
  We introduce CanaryBench, a simple and reproducible stress test for privacy leakage in cluster-level conversation summaries.<n>CanaryBench generates synthetic conversations with planted secret strings ("canaries") that simulate sensitive identifiers.<n>We observe canary leakage in 50 of 52 canary-containing clusters, along with nonzero-based PII indicator counts.
  arXiv  Detail & Related papers  (2026-01-25T20:30:37Z)
• Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models [47.866853046761044]
  We find that diverse, subtle patterns in training data can degrade contextual privacy.<n>Fine-tuned models lose their ability to reason about contextual privacy norms.<n>Our results reveal a critical gap in current safety evaluations.
  arXiv  Detail & Related papers  (2026-01-21T17:53:06Z)
• PrivacyBench: A Conversational Benchmark for Evaluating Privacy in Personalized AI [8.799432439533211]
  AI agents rely on access to a user's digital footprint, which often includes sensitive data from private emails, chats and purchase histories.<n>This access creates a fundamental societal and privacy risk.<n>We introduce PrivacyBench, a benchmark with socially grounded datasets containing embedded secrets.
  arXiv  Detail & Related papers  (2025-12-31T13:16:45Z)
• VoxGuard: Evaluating User and Attribute Privacy in Speech via Membership Inference Attacks [51.68795949691009]
  We introduce VoxGuard, a framework grounded in differential privacy and membership inference.<n>For attributes, we show that simple transparent attacks recover gender and accent with near-perfect accuracy even after anonymization.<n>Our results demonstrate that EER substantially underestimates leakage, highlighting the need for low-FPR evaluation.
  arXiv  Detail & Related papers  (2025-09-22T20:57:48Z)
• On the MIA Vulnerability Gap Between Private GANs and Diffusion Models [51.53790101362898]
  Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis.<n>We present the first unified theoretical and empirical analysis of the privacy risks faced by differentially private generative models.
  arXiv  Detail & Related papers  (2025-09-03T14:18:22Z)
• A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage [77.83757117924995]
  We propose a new framework that evaluates re-identification attacks to quantify individual privacy risks upon data release.<n>Our approach shows that seemingly innocuous auxiliary information can be used to infer sensitive attributes like age or substance use history from sanitized data.
  arXiv  Detail & Related papers  (2025-04-28T01:16:27Z)
• Quantifying Privacy Leakage in Split Inference via Fisher-Approximated Shannon Information Analysis [1.4972864129791565]
  Split inference (SI) partitions deep neural networks into distributed sub-models, enabling privacy-preserving collaborative learning.<n>Despite extensive research on adversarial attack-defense games, a shortfall remains in the fundamental analysis of privacy risks.<n>This paper establishes a theoretical framework for privacy leakage quantification using information theory, defining it as the adversary's certainty and deriving both average-case and worst-case error bounds.
  arXiv  Detail & Related papers  (2025-04-14T09:19:06Z)
• The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasets [12.730435519914415]
  We examine the privacy metrics used in real-world synthetic data deployments and demonstrate their unreliability in several ways.<n>We introduce ReconSyn, a reconstruction attack that generates multiple synthetic datasets that are considered private by the metrics but actually leak unique information to individual records.<n>We show that ReconSyn recovers 78-100% of the outliers in the train data with only black-box access to a single fitted generative model and the privacy metrics.
  arXiv  Detail & Related papers  (2023-12-08T15:42:28Z)
• InfoScrub: Towards Attribute Privacy by Targeted Obfuscation [77.49428268918703]
  We study techniques that allow individuals to limit the private information leaked in visual data. We tackle this problem in a novel image obfuscation framework. We find our approach generates obfuscated images faithful to the original input images, and additionally increase uncertainty by 6.2$times$ (or up to 0.85 bits) over the non-obfuscated counterparts.
  arXiv  Detail & Related papers  (2020-05-20T19:48:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.