PANORAMA: A synthetic PII-laced dataset for studying sensitive data memorization in LLMs

• URL: http://arxiv.org/abs/2505.12238v1
• Date: Sun, 18 May 2025 05:27:35 GMT
• Title: PANORAMA: A synthetic PII-laced dataset for studying sensitive data memorization in LLMs
• Authors: Sriram Selvam, Anneswa Ghosh,
• Abstract summary: memorization of sensitive and personally identifiable information poses growing privacy risks.<n>Existing efforts to study sensitive and PII data memorization and develop mitigation strategies are hampered by the absence of realistic datasets.<n>We introduce PANORAMA - Profile-based Assemblage for Naturalistic Online Representation and Attribute Memorization Analysis.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The memorization of sensitive and personally identifiable information (PII) by large language models (LLMs) poses growing privacy risks as models scale and are increasingly deployed in real-world applications. Existing efforts to study sensitive and PII data memorization and develop mitigation strategies are hampered by the absence of comprehensive, realistic, and ethically sourced datasets reflecting the diversity of sensitive information found on the web. We introduce PANORAMA - Profile-based Assemblage for Naturalistic Online Representation and Attribute Memorization Analysis, a large-scale synthetic corpus of 384,789 samples derived from 9,674 synthetic profiles designed to closely emulate the distribution, variety, and context of PII and sensitive data as it naturally occurs in online environments. Our data generation pipeline begins with the construction of internally consistent, multi-attribute human profiles using constrained selection to reflect real-world demographics such as education, health attributes, financial status, etc. Using a combination of zero-shot prompting and OpenAI o3-mini, we generate diverse content types - including wiki-style articles, social media posts, forum discussions, online reviews, comments, and marketplace listings - each embedding realistic, contextually appropriate PII and other sensitive information. We validate the utility of PANORAMA by fine-tuning the Mistral-7B model on 1x, 5x, 10x, and 25x data replication rates with a subset of data and measure PII memorization rates - revealing not only consistent increases with repetition but also variation across content types, highlighting PANORAMA's ability to model how memorization risks differ by context. Our dataset and code are publicly available, providing a much-needed resource for privacy risk assessment, model auditing, and the development of privacy-preserving LLMs.

Related papers

• SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy [0.0]
  We investigate capability of Large Language Models (Ms) to generate synthetic datasets with Differential Privacy (DP) mechanisms.<n>Our approach incorporates DP-based noise injection methods, including Laplace and Gaussian distributions, into the data generation process.<n>We then evaluate the utility of these DP-enhanced synthetic datasets by comparing the performance of ML models trained on them against models trained on the original data.
  arXiv  Detail & Related papers  (2024-12-30T01:10:10Z)
• Tabular Data Synthesis with Differential Privacy: A Survey [24.500349285858597]
  Data sharing is a prerequisite for collaborative innovation, enabling organizations to leverage diverse datasets for deeper insights. Data synthesis tackles this by generating artificial datasets that preserve the statistical characteristics of real data. Differentially private data synthesis has emerged as a promising approach to privacy-aware data sharing.
  arXiv  Detail & Related papers  (2024-11-04T06:32:48Z)
• KIPPS: Knowledge infusion in Privacy Preserving Synthetic Data Generation [0.0]
  Generative Deep Learning models struggle to model discrete and non-Gaussian features that have domain constraints. Generative models create synthetic data that repeats sensitive features, which is a privacy risk. This paper proposes a novel model, KIPPS, that infuses Domain and Regulatory Knowledge from Knowledge Graphs into Generative Deep Learning models for enhanced Privacy Preserving Synthetic data generation.
  arXiv  Detail & Related papers  (2024-09-25T19:50:03Z)
• Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data [18.984529269623135]
  This study investigates whether fine-tuning with generated data truly enhances privacy or introduces additional privacy risks.<n>We use the Pythia Model Suite and Open Pre-trained Transformer to measure privacy risks.
  arXiv  Detail & Related papers  (2024-09-12T10:14:12Z)
• LLM-PBE: Assessing Data Privacy in Large Language Models [111.58198436835036]
  Large Language Models (LLMs) have become integral to numerous domains, significantly advancing applications in data management, mining, and analysis. Despite the critical nature of this issue, there has been no existing literature to offer a comprehensive assessment of data privacy risks in LLMs. Our paper introduces LLM-PBE, a toolkit crafted specifically for the systematic evaluation of data privacy risks in LLMs.
  arXiv  Detail & Related papers  (2024-08-23T01:37:29Z)
• Robust Utility-Preserving Text Anonymization Based on Large Language Models [80.5266278002083]
  Text anonymization is crucial for sharing sensitive data while maintaining privacy. Existing techniques face the emerging challenges of re-identification attack ability of Large Language Models. This paper proposes a framework composed of three LLM-based components -- a privacy evaluator, a utility evaluator, and an optimization component.
  arXiv  Detail & Related papers  (2024-07-16T14:28:56Z)
• Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data [51.41288763521186]
  Retrieval-augmented generation (RAG) enhances the outputs of language models by integrating relevant information retrieved from external knowledge sources.<n>RAG systems may face severe privacy risks when retrieving private data.<n>We propose using synthetic data as a privacy-preserving alternative for the retrieval data.
  arXiv  Detail & Related papers  (2024-06-20T22:53:09Z)
• FewFedPIT: Towards Privacy-preserving and Few-shot Federated Instruction Tuning [54.26614091429253]
  Federated instruction tuning (FedIT) is a promising solution, by consolidating collaborative training across multiple data owners. FedIT encounters limitations such as scarcity of instructional data and risk of exposure to training data extraction attacks. We propose FewFedPIT, designed to simultaneously enhance privacy protection and model performance of federated few-shot learning.
  arXiv  Detail & Related papers  (2024-03-10T08:41:22Z)
• 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)
• Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation [117.3856882511919]
  We propose the Style-HAllucinated Dual consistEncy learning (SHADE) framework to handle domain shift. Our SHADE yields significant improvement and outperforms state-of-the-art methods by 5.07% and 8.35% on the average mIoU of three real-world datasets.
  arXiv  Detail & Related papers  (2022-04-06T02:49:06Z)
• Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification [101.1886788396803]
  Person re-identification (re-ID) has gained more and more attention due to its widespread applications in video surveillance. Unfortunately, the mainstream deep learning methods still need a large quantity of labeled data to train models. In this paper, we develop a data collector to automatically generate synthetic re-ID samples in a computer game, and construct a data labeler to simultaneously annotate them.
  arXiv  Detail & Related papers  (2021-09-12T15:51:41Z)

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.