Membership Inference Attacks against Large Vision-Language Models

• URL: http://arxiv.org/abs/2411.02902v1
• Date: Tue, 05 Nov 2024 08:35:08 GMT
• Title: Membership Inference Attacks against Large Vision-Language Models
• Authors: Zhan Li, Yongtao Wu, Yihang Chen, Francesco Tonin, Elias Abad Rocamora, Volkan Cevher,
• Abstract summary: Large vision-language models (VLLMs) exhibit promising capabilities for processing multi-modal tasks across various application scenarios. Their emergence also raises significant data security concerns, given the potential inclusion of sensitive information, such as private photos and medical records. Detecting inappropriately used data in VLLMs remains a critical and unresolved issue.
• Score: 40.996912464828696
• License:
• Abstract: Large vision-language models (VLLMs) exhibit promising capabilities for processing multi-modal tasks across various application scenarios. However, their emergence also raises significant data security concerns, given the potential inclusion of sensitive information, such as private photos and medical records, in their training datasets. Detecting inappropriately used data in VLLMs remains a critical and unresolved issue, mainly due to the lack of standardized datasets and suitable methodologies. In this study, we introduce the first membership inference attack (MIA) benchmark tailored for various VLLMs to facilitate training data detection. Then, we propose a novel MIA pipeline specifically designed for token-level image detection. Lastly, we present a new metric called MaxR\'enyi-K%, which is based on the confidence of the model output and applies to both text and image data. We believe that our work can deepen the understanding and methodology of MIAs in the context of VLLMs. Our code and datasets are available at https://github.com/LIONS-EPFL/VL-MIA.

Related papers

• Membership Inference Attacks Against Vision-Language Models [24.47069867575367]
  Vision-Language Models (VLMs) have shown exceptional multi-modal understanding and dialog capabilities. Risks of data misuse and leakage have been largely unexplored. We propose four membership inference methods, each tailored to different levels of background knowledge.
  arXiv  Detail & Related papers  (2025-01-27T05:44:58Z)
• Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach [56.55633052479446]
  Web-scale visual entity recognition presents significant challenges due to the lack of clean, large-scale training data. We propose a novel methodology to curate such a dataset, leveraging a multimodal large language model (LLM) for label verification, metadata generation, and rationale explanation. Experiments demonstrate that models trained on this automatically curated data achieve state-of-the-art performance on web-scale visual entity recognition tasks.
  arXiv  Detail & Related papers  (2024-10-31T06:55:24Z)
• Context is Key: A Benchmark for Forecasting with Essential Textual Information [87.3175915185287]
  "Context is Key" (CiK) is a forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context. We evaluate a range of approaches, including statistical models, time series foundation models, and LLM-based forecasters. We propose a simple yet effective LLM prompting method that outperforms all other tested methods on our benchmark.
  arXiv  Detail & Related papers  (2024-10-24T17:56:08Z)
• Detecting Training Data of Large Language Models via Expectation Maximization [62.28028046993391]
  Membership inference attacks (MIAs) aim to determine whether a specific instance was part of a target model's training data. Applying MIAs to large language models (LLMs) presents unique challenges due to the massive scale of pre-training data and the ambiguous nature of membership. We introduce EM-MIA, a novel MIA method for LLMs that iteratively refines membership scores and prefix scores via an expectation-maximization algorithm.
  arXiv  Detail & Related papers  (2024-10-10T03:31:16Z)
• Advancing Multimodal Large Language Models in Chart Question Answering with Visualization-Referenced Instruction Tuning [1.6570772838074355]
  multimodal large language models (MLLMs) exhibit great potential for chart question answering (CQA) Recent efforts primarily focus on scaling up training datasets through data collection and synthesis. We propose a visualization-referenced instruction tuning approach to guide the training dataset enhancement and model development.
  arXiv  Detail & Related papers  (2024-07-29T17:04:34Z)
• SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
  Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM. We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
  arXiv  Detail & Related papers  (2024-07-16T04:41:58Z)
• Security Vulnerability Detection with Multitask Self-Instructed Fine-Tuning of Large Language Models [8.167614500821223]
  We introduce MSIVD, multitask self-instructed fine-tuning for vulnerability detection, inspired by chain-of-thought prompting and LLM self-instruction. Our experiments demonstrate that MSIVD achieves superior performance, outperforming the highest LLM-based vulnerability detector baseline (LineVul) with a F1 score of 0.92 on the BigVul dataset, and 0.48 on the PreciseBugs dataset.
  arXiv  Detail & Related papers  (2024-06-09T19:18:05Z)
• Why are Visually-Grounded Language Models Bad at Image Classification? [39.76294811955341]
  We revisit the image classification task using visually-grounded language models (VLMs) such as GPT-4V and LLaVA. We find that existing proprietary and public VLMs significantly underperform CLIP on standard image classification benchmarks like ImageNet. Our analysis reveals that the primary cause is data-related: critical information for image classification is encoded in the VLM's latent space but can only be effectively decoded with enough training data.
  arXiv  Detail & Related papers  (2024-05-28T17:57:06Z)
• Do Membership Inference Attacks Work on Large Language Models? [141.2019867466968]
  Membership inference attacks (MIAs) attempt to predict whether a particular datapoint is a member of a target model's training data. We perform a large-scale evaluation of MIAs over a suite of language models trained on the Pile, ranging from 160M to 12B parameters. We find that MIAs barely outperform random guessing for most settings across varying LLM sizes and domains.
  arXiv  Detail & Related papers  (2024-02-12T17:52:05Z)

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.