Little Data, Big Impact: Privacy-Aware Visual Language Models via Minimal Tuning

• URL: http://arxiv.org/abs/2405.17423v3
• Date: Sat, 24 May 2025 12:11:24 GMT
• Title: Little Data, Big Impact: Privacy-Aware Visual Language Models via Minimal Tuning
• Authors: Laurens Samson, Nimrod Barazani, Sennay Ghebreab, Yuki M. Asano,
• Abstract summary: We evaluate tenofthe-art Visual As Language Models (VLMs) and identify limitations in their understanding of visual privacy.<n>To address this, we introduce two compact, high-quality benchmarks, PrivBench-H and PrivTune.<n>We obtain substantial gains on all benchmarks, surpassing GPT-4, while maintaining strong performance on other tasks.
• Score: 16.272314073324626
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As Visual Language Models (VLMs) become increasingly embedded in everyday applications, ensuring they can recognize and appropriately handle privacy-sensitive content is essential. We conduct a comprehensive evaluation of ten state-of-the-art VLMs and identify limitations in their understanding of visual privacy. Existing datasets suffer from label inconsistencies, limiting their reliability. To address this, we introduce two compact, high-quality benchmarks, PrivBench and PrivBench-H, that focus on commonly recognized privacy categories aligned with the General Data Protection Regulation (GDPR). Additionally, we present PrivTune, an instruction-tuning dataset specifically curated to improve privacy sensitivity. We obtain a Privacy VLM by fine-tuning an off-the-shelf VLM on only 100 samples from PrivTune, which leads to substantial gains on all benchmarks, surpassing GPT-4, while maintaining strong performance on other tasks. Our findings show that privacy-awareness in VLMs can be substantially improved with minimal data and careful dataset design, setting the stage for safer, more privacy-aligned AI systems.

Related papers

• 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)
• PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance [44.287734754038254]
  We present PrivaCI-Bench, a contextual privacy evaluation benchmark for generative large language models (LLMs)<n>We evaluate the latest LLMs, including the recent reasoner models QwQ-32B and Deepseek R1.<n>Our experimental results suggest that though LLMs can effectively capture key CI parameters inside a given context, they still require further advancements for privacy compliance.
  arXiv  Detail & Related papers  (2025-02-24T10:49:34Z)
• 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) Based on Multi-P$2$A, we evaluate the privacy preservation capabilities of 21 open-source and 2 closed-source LVLMs. Our results reveal that current LVLMs generally pose a high risk of facilitating privacy breaches.
  arXiv  Detail & Related papers  (2024-12-27T07:33:39Z)
• On Active Privacy Auditing in Supervised Fine-tuning for White-Box Language Models [7.275432177367344]
  Parsing is designed to identify and quantify privacy leakage risks during the supervised fine-tuning of language models (LMs) We have improved the effectiveness of white-box membership inference attacks (MIAs) on large LMs including GPT-2, Llama2, and certain variants of them. Our research aims to provide the SFT community of LMs with a reliable, ready-to-use privacy auditing tool, and to offer valuable insights into safeguarding privacy during the fine-tuning process.
  arXiv  Detail & Related papers  (2024-11-11T15:46:07Z)
• Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset [94.13848736705575]
  We introduce Facial Identity Unlearning Benchmark (FIUBench), a novel VLM unlearning benchmark designed to robustly evaluate the effectiveness of unlearning algorithms. We apply a two-stage evaluation pipeline that is designed to precisely control the sources of information and their exposure levels. Through the evaluation of four baseline VLM unlearning algorithms within FIUBench, we find that all methods remain limited in their unlearning performance.
  arXiv  Detail & Related papers  (2024-11-05T23:26:10Z)
• PV-VTT: A Privacy-Centric Dataset for Mission-Specific Anomaly Detection and Natural Language Interpretation [5.0923114224599555]
  We present PV-VTT (Privacy Violation Video To Text), a unique multimodal dataset aimed at identifying privacy violations. PV-VTT provides detailed annotations for both video and text in scenarios. This privacy-focused approach allows researchers to use the dataset while protecting participant confidentiality.
  arXiv  Detail & Related papers  (2024-10-30T01:02:20Z)
• 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. We instantiate PrivacyLens with a collection of privacy norms grounded in privacy literature and crowdsourced seeds. 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)
• The Phantom Menace: Unmasking Privacy Leakages in Vision-Language Models [31.166994121531232]
  Vision-Language Models (VLMs) combine visual and textual understanding, rendering them well-suited for diverse tasks. These capabilities are built upon training on large amount of uncurated data crawled from the web. In this paper, we assess whether these vulnerabilities exist, focusing on identity leakage.
  arXiv  Detail & Related papers  (2024-08-02T12:36:13Z)
• Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning [62.224804688233]
  differential privacy (DP) offers a promising solution by ensuring models are 'almost indistinguishable' with or without any particular privacy unit. We study user-level DP motivated by applications where it necessary to ensure uniform privacy protection across users.
  arXiv  Detail & Related papers  (2024-06-20T13:54:32Z)
• PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs [55.8550939439138]
  Vision-Language Models (VLMs) have shown immense potential by integrating large language models with vision systems. These models face challenges in the fundamental computer vision task of object localisation, due to their training on multimodal data containing mostly captions. We introduce an input-agnostic Positional Insert (PIN), a learnable spatial prompt, containing a minimal set of parameters that are slid inside the frozen VLM. Our PIN module is trained with a simple next-token prediction task on synthetic data without requiring the introduction of new output heads.
  arXiv  Detail & Related papers  (2024-02-13T18:39:18Z)
• Personalized Differential Privacy for Ridge Regression [3.4751583941317166]
  We introduce our novel Personalized-DP Output Perturbation method ( PDP-OP) that enables to train Ridge regression models with individual per data point privacy levels. We provide rigorous privacy proofs for our PDP-OP as well as accuracy guarantees for the resulting model. We show that PDP-OP outperforms the personalized privacy techniques of Jorgensen et al.
  arXiv  Detail & Related papers  (2024-01-30T16:00:14Z)
• PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models [42.20437015301152]
  We present PrivLM-Bench, a benchmark for evaluating the privacy leakage of language models (LMs) Instead of only reporting DP parameters, PrivLM-Bench sheds light on the neglected inference data privacy during actual usage. We conduct extensive experiments on three datasets of GLUE for mainstream LMs.
  arXiv  Detail & Related papers  (2023-11-07T14:55:52Z)
• Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory [82.7042006247124]
  We show that even the most capable AI models reveal private information in contexts that humans would not, 39% and 57% of the time, respectively. Our work underscores the immediate need to explore novel inference-time privacy-preserving approaches, based on reasoning and theory of mind.
  arXiv  Detail & Related papers  (2023-10-27T04:15:30Z)
• PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners [81.571305826793]
  We introduce Contextual Privacy Protection Language Models (PrivacyMind) Our work offers a theoretical analysis for model design and benchmarks various techniques. In particular, instruction tuning with both positive and negative examples stands out as a promising method.
  arXiv  Detail & Related papers  (2023-10-03T22:37:01Z)
• Mean Estimation Under Heterogeneous Privacy: Some Privacy Can Be Free [13.198689566654103]
  This work considers the problem of mean estimation under heterogeneous Differential Privacy constraints. The algorithm we propose is shown to be minimax optimal when there are two groups of users with distinct privacy levels.
  arXiv  Detail & Related papers  (2023-04-27T05:23:06Z)
• How Do Input Attributes Impact the Privacy Loss in Differential Privacy? [55.492422758737575]
  We study the connection between the per-subject norm in DP neural networks and individual privacy loss. We introduce a novel metric termed the Privacy Loss-Input Susceptibility (PLIS) which allows one to apportion the subject's privacy loss to their input attributes.
  arXiv  Detail & Related papers  (2022-11-18T11:39:03Z)
• Privacy-Adaptive BERT for Natural Language Understanding [20.821155542969947]
  We study how to improve the effectiveness of NLU models under a Local Privacy setting using BERT. We propose privacy-adaptive LM pretraining methods and demonstrate that they can significantly improve model performance on privatized text input.
  arXiv  Detail & Related papers  (2021-04-15T15:01:28Z)

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.