Seeing Without Exposing: Adaptive Privacy Control for Open-World, Context-Hungry MLLMs

• URL: http://arxiv.org/abs/2606.07175v1
• Date: Fri, 05 Jun 2026 11:41:39 GMT
• Title: Seeing Without Exposing: Adaptive Privacy Control for Open-World, Context-Hungry MLLMs
• Abstract summary: We propose Anchored Privacy Drifting (APD) to tackle privacy challenges in MLLMs.<n>APD drifts privacy-sensitive elements toward semantically equivalent alternatives while anchoring contextual cues to the source image.<n>We show that our method achieves balanced improvements in both privacy sanitization and content retention.
• Score: 61.80513991207956
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal large language models (MLLMs) have raised new privacy challenges. On the data side, user-provided inputs often include unpredictable sensitive information; while on the downstream task side, model reasoning depends on rich visual context that may itself be privacy-sensitive. Existing privacy protection methods, however, rely on predefined sensitive categories and fixed obfuscation strategies, struggling to tackle such challenges in MLLMs. To address this dilemma, we propose Anchored Privacy Drifting (APD), a training-free method that drifts privacy-sensitive elements toward semantically equivalent alternatives while anchoring contextual cues to the source image. To systematically evaluate this dual objective of privacy protection and contextual preservation, we introduce AdaptShield, a comprehensive benchmark covering 22 privacy categories, which combines conventional privacy metrics with MLLM-based assessments of contextual utility. Extensive experiments show that our method achieves balanced improvements in both privacy sanitization and content retention, with average gains of 10.4% on textual categories and 8.5% under MLLM-based evaluation across four MLLM series, i.e., Qwen2.5, Qwen3, InternVL3, and InternVL3.5.

Related papers

• Beyond Visual Evidence: Revealing and Mitigating Relational Privacy Leakage in Document MLLMs [13.913126694995668]
  This paper investigates the privacy issues inherent in Key Information Extraction (KIE) tasks.<n>We reveal that when input images lack sufficient visual evidence, these models often rely on memorized field relations to infer missing content.<n>We propose mitigating this risk with the Unlearning Framework (DRUF) which comprises a dynamic update mechanism.
  arXiv  Detail & Related papers  (2026-08-13T07:53:53Z)
• Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges [55.425628316813174]
  Multi-modal Large Language Models (MLLMs) process both text and images.<n>Compared to text-only models, MLLMs can extract and expose sensitive information embedded in images.<n>Some MLLMs are susceptible to privacy breaches, leaking sensitive data embedded in images or stored in memory.
  arXiv  Detail & Related papers  (2026-06-08T07:19:42Z)
• When Visual Privacy Protection Meets Multimodal Large Language Models [28.059357669311666]
  We propose a novel framework to seek a better trade-off between visual privacy and MLLM's performance.<n>Our method is effective on different benchmarks.
  arXiv  Detail & Related papers  (2026-03-14T15:15:32Z)
• VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models [25.266028200777317]
  Speech Language Models (SLMs) are expected to distinguish between users to manage information flow appropriately.<n>Current SLM benchmarks test dialogue ability but overlook speaker identity.<n>We introduce VoxPrivacy, the first benchmark designed to evaluate interactional privacy in SLMs.
  arXiv  Detail & Related papers  (2026-01-27T06:22:14Z)
• Who Can See Through You? Adversarial Shielding Against VLM-Based Attribute Inference Attacks [13.326888254423901]
  VLM-based attribute inference attacks have emerged as a serious privacy concern, enabling adversaries to infer private attributes from images shared on social media.<n>We propose a novel protection method that jointly optimize privacy suppression and utility preservation under a visual consistency constraint.<n>Our method effectively reduces PAR below 25%, keeps NPAR above 88%, and generalizes well to unseen and paraphrased privacy questions.
  arXiv  Detail & Related papers  (2025-12-20T08:08:50Z)
• When Privacy Meets Recovery: The Overlooked Half of Surrogate-Driven Privacy Preservation for MLLM Editing [61.80513991207956]
  This work focuses on the challenge of how to restore surrogate-driven protected data in diverse MLLM scenarios.<n>We first bridge this research gap by contributing the SPPE (Surrogate Privacy Protected Editable) dataset.<n>We introduce a unified approach that reliably reconstructs private content while preserving the fidelity of MLLM-generated edits.
  arXiv  Detail & Related papers  (2025-12-08T04:59:03Z)
• PRISM: Privacy-Aware Routing for Adaptive Cloud-Edge LLM Inference via Semantic Sketch Collaboration [8.776463501718737]
  We propose a context-aware framework that dynamically balances privacy and inference quality.<n>PRISM executes in four stages: (1) the edge device profiles entity-level sensitivity; (2) a soft gating module on the edge selects an execution mode - cloud, edge, or collaboration; (3) for collaborative paths, the edge applies adaptive two-layer local differential privacy based on entity risks; and (4) the cloud LLM generates a semantic sketch from the perturbed prompt.
  arXiv  Detail & Related papers  (2025-11-27T22:32:33Z)
• MAGPIE: A dataset for Multi-AGent contextual PrIvacy Evaluation [54.410825977390274]
  Existing benchmarks to evaluate contextual privacy in LLM-agents primarily assess single-turn, low-complexity tasks.<n>We first present a benchmark - MAGPIE comprising 158 real-life high-stakes scenarios across 15 domains.<n>We then evaluate the current state-of-the-art LLMs on their understanding of contextually private data and their ability to collaborate without violating user privacy.
  arXiv  Detail & Related papers  (2025-06-25T18:04:25Z)
• Multi-P$^2$A: A Multi-perspective Benchmark on Privacy Assessment for Large Vision-Language Models [65.2761254581209]
  We evaluate the privacy preservation capabilities of 21 open-source and 2 closed-source Large Vision-Language Models (LVLMs)<n>Based on Multi-P$2$A, we evaluate the privacy preservation capabilities of 21 open-source and 2 closed-source LVLMs.<n>Our results reveal that current LVLMs generally pose a high risk of facilitating privacy breaches.
  arXiv  Detail & Related papers  (2024-12-27T07:33:39Z)
• PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action [54.11479432110771]
  PrivacyLens is a novel framework designed to extend privacy-sensitive seeds into expressive vignettes and further into agent trajectories.<n>We instantiate PrivacyLens with a collection of privacy norms grounded in privacy literature and crowdsourced seeds.<n>State-of-the-art LMs, like GPT-4 and Llama-3-70B, leak sensitive information in 25.68% and 38.69% of cases, even when prompted with privacy-enhancing instructions.
  arXiv  Detail & Related papers  (2024-08-29T17:58:38Z)

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.