From Multiplicity to Vulnerability: Privacy Amplification Risk from One-Dataset-Multiple-Model Exposure

• URL: http://arxiv.org/abs/2607.05111v1
• Date: Mon, 06 Jul 2026 14:04:39 GMT
• Title: From Multiplicity to Vulnerability: Privacy Amplification Risk from One-Dataset-Multiple-Model Exposure
• Abstract summary: This work reveals that the one-dataset-multiple-model (ODMM) setting substantially amplifies privacy leakage.<n>Under black-box access to ODMM models, we design an aggregation mechanism that collectively captures carefully identified privacy signals leaked by individual ODMM models.<n>Our results provide strong evidence that dataset reuse across ODMM models strikingly jeopardizes privacy.
• Score: 18.343372735919292
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: To efficiently exploit a valuable data source (e.g., facial or medical images), it is frequently harnessed to fulfill multiple learning objectives (e.g., facial recognition, age estimation, and race classification). Each trained model is then deployed as an independent API service for corresponding inference. However, the privacy risk introduced by this one-dataset-multiple-model (ODMM) paradigm is completely overlooked by the community. For the first time, this work reveals that the ODMM setting substantially amplifies privacy leakage. We establish a theoretical framework that proves that privacy leakage accumulates as more ODMM models are exposed, a phenomenon we term ODMM privacy composition. Guided by this theoretical foundation, we propose PRIME (Privacy Amplification RIsk from One-Dataset-Multiple-Model Exposure) to systematically assess this risk and quantify the resulting leakage using membership inference attacks (MIAs). Under black-box access to ODMM models, we design an aggregation mechanism that collectively captures carefully identified privacy signals leaked by individual ODMM models, and construct an attack meta-classifier over the aggregated meta-information to infer the membership status of a given sample jointly. Our results provide strong evidence that dataset reuse across ODMM models strikingly jeopardizes privacy, which is consistently evident across five privacy-sensitive image and textual benchmark datasets and diverse model architectures (from ResNet and ViT to Qwen3-1.7B), spanning three domains: facial analysis, medical imaging, and textual attribution analysis. While mitigations such as differential privacy can reduce the effectiveness of PRIME with trade-offs, our attack still consistently outperforms single-task MIAs.

Related papers

• Noise as a Probe: Membership Inference Attacks on Diffusion Models Leveraging Initial Noise [51.179816451161635]
  Diffusion models have achieved remarkable progress in image generation, but their increasing deployment raises serious concerns about privacy.<n>In this work, we utilize a critical yet overlooked vulnerability: the widely used noise schedules fail to fully eliminate semantic information in the images.<n>We propose a simple yet effective membership inference attack, which injects semantic information into the initial noise and infers membership by analyzing the model's generation result.
  arXiv  Detail & Related papers  (2026-01-29T12:29:01Z)
• 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)
• Auditing M-LLMs for Privacy Risks: A Synthetic Benchmark and Evaluation Framework [7.493288948235459]
  PRISM is a large-scale synthetic benchmark designed to evaluate cross-modal privacy risks.<n> PRISM is the first multi-modal, multi-dimensional and fine-grained synthesized dataset.<n>We evaluate the inference capabilities of six leading M-LLMs on PRISM.
  arXiv  Detail & Related papers  (2025-11-05T07:23:21Z)
• 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)
• Ensembling Membership Inference Attacks Against Tabular Generative Models [7.709474360794182]
  In realistic threat scenarios, an adversary must choose a single method without a priori guarantee that it will be the empirically highest performing option.<n>We study this challenge as a decision theoretic problem under uncertainty and conduct the largest synthetic data privacy benchmark to date.<n>Motivated by these findings, we propose ensemble MIAs and show that unsupervised ensembles built on individual attacks offer empirically more robust, regret-minimizing strategies than individual attacks.
  arXiv  Detail & Related papers  (2025-09-02T18:44:07Z)
• MrM: Black-Box Membership Inference Attacks against Multimodal RAG Systems [31.53306157650065]
  Multimodal retrieval-augmented generation (RAG) systems enhance large vision-language models by integrating cross-modal knowledge.<n>These knowledge databases may contain sensitive information that requires privacy protection.<n>MrM is the first black-box MIA framework targeted at multimodal RAG systems.
  arXiv  Detail & Related papers  (2025-06-09T03:48:50Z)
• Differentially Private Distribution Release of Gaussian Mixture Models via KL-Divergence Minimization [11.3783762550703]
  We introduce a DP mechanism that adds carefully calibrated random perturbations to the GMM parameters.<n>Our approach achieves strong privacy guarantees while maintaining high utility.
  arXiv  Detail & Related papers  (2025-06-04T00:40:24Z)
• Communication-Efficient and Privacy-Adaptable Mechanism for Federated Learning [54.20871516148981]
  We introduce the Communication-Efficient and Privacy-Adaptable Mechanism (CEPAM)<n>CEPAM achieves communication efficiency and privacy protection simultaneously.<n>We theoretically analyze the privacy guarantee of CEPAM and investigate the trade-offs among user privacy and accuracy of CEPAM.
  arXiv  Detail & Related papers  (2025-01-21T11:16:05Z)
• Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models [112.48136829374741]
  In this paper, we unveil a new vulnerability: the privacy backdoor attack. When a victim fine-tunes a backdoored model, their training data will be leaked at a significantly higher rate than if they had fine-tuned a typical model. Our findings highlight a critical privacy concern within the machine learning community and call for a reevaluation of safety protocols in the use of open-source pre-trained models.
  arXiv  Detail & Related papers  (2024-04-01T16:50:54Z)
• CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning [63.72975421109622]
  CleanCLIP is a finetuning framework that weakens the learned spurious associations introduced by backdoor attacks. CleanCLIP maintains model performance on benign examples while erasing a range of backdoor attacks on multimodal contrastive learning.
  arXiv  Detail & Related papers  (2023-03-06T17:48:32Z)
• Membership Inference Attacks against Synthetic Data through Overfitting Detection [84.02632160692995]
  We argue for a realistic MIA setting that assumes the attacker has some knowledge of the underlying data distribution. We propose DOMIAS, a density-based MIA model that aims to infer membership by targeting local overfitting of the generative model.
  arXiv  Detail & Related papers  (2023-02-24T11:27:39Z)

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.