Beyond Direct Identifiers: Probabilistic Privacy Risk Estimation for Privacy-Conscious LLM Query Delegation

• URL: http://arxiv.org/abs/2608.09140v1
• Date: Mon, 10 Aug 2026 05:38:28 GMT
• Title: Beyond Direct Identifiers: Probabilistic Privacy Risk Estimation for Privacy-Conscious LLM Query Delegation
• Abstract summary: Privacy risk does not stem solely from explicit identifiers but also PII-free self-disclosures.<n>We propose k-anonymity as a useful auxiliary metric for tackling Privacy-Conscious Delegation.
• Score: 20.31515213689976
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent work on protecting privacy during user-LLM interactions often focuses on direct, explicit identifiers: the personally-identifiable information (PII) captured by standard detectors. One such approach is Privacy-Conscious Delegation (PCD), where a local LLM acts as an intermediary. However, privacy risk does not stem solely from explicit identifiers but also PII-free self-disclosures, leaving users identifiable through combinations of quasi-identifying traits. We investigate a probabilistic variant of PCD, where we augment its objectives with an LLM-driven probabilistic estimation of k-anonymity. To facilitate this, we first create the PUPA-SD dataset, which contains naturalistic user queries with self-disclosure. Our preliminary results indicate that optimizing PAPILLON on PUPA-SD improves quality on unseen conversations across a variety of local models and produces the best privacy-utility balance for Llama-3.2-3B, while smaller models struggle to jointly optimize quality and privacy. We propose k-anonymity as a useful auxiliary metric for tackling PCD.

Related papers

• Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models [35.164227002323706]
  We investigate privacy risks under DP adaptations in large language models (LLMs)<n>We benchmark these risks using state-of-the-art attacks such as robust membership inference and canary data extraction.<n>We find that parameter-efficient fine-tuning methods, such as LoRA, achieve the highest empirical privacy protection for OOD data.
  arXiv  Detail & Related papers  (2026-06-08T12:21:02Z)
• IDP-Bench: Benchmarking ability of LLMs to protect personal information in interdependent privacy contexts [15.026169063578697]
  Large language models (LLMs) are becoming widely deployed as personal AI assistants with access to sensitive user data.<n>Prior work focuses mainly on individual-level risks, overlooking textbfinterdependent privacy (IDP)--where one person's data may be revealed by others without their knowledge or consent.<n>We introduce textbfIDP-Bench: the first LLM benchmark for IDP scenarios, grounded in the Contextual Integrity (CI) framework.
  arXiv  Detail & Related papers  (2026-06-06T07:59:08Z)
• Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents [52.02752011119451]
  We investigate privacy perception in the real world through the lens of human awareness.<n>We propose the PrivacyIceberg, which categorizes real-world human privacy risks into three tiers.
  arXiv  Detail & Related papers  (2026-05-07T13:21:44Z)
• 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)
• PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER) [45.870212237420226]
  This work explores the use of Named- Entity Recognition (NER) to facilitate the privacy-preserving training of Large Language Models (LLMs)<n>We propose a framework that uses NER technologies to anonymize sensitive information in text data, such as personal identities or geographic locations.<n>The study involved two language models (BERT and RoBERTa) and six anonymization algorithms (based on Presidio, FLAIR, BERT, and different versions of GPT) applied to a database of 24,000 candidate profiles.
  arXiv  Detail & Related papers  (2025-06-30T14:42:49Z)
• Evaluating Differential Privacy on Correlated Datasets Using Pointwise Maximal Leakage [38.4830633082184]
  Data-driven advancements pose substantial risks to privacy.<n> differential privacy has become a cornerstone in privacy preservation efforts.<n>Our work aims to foster a deeper understanding of subtle privacy risks and highlight the need for the development of more effective privacy-preserving mechanisms.
  arXiv  Detail & Related papers  (2025-02-08T10:30:45Z)
• 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)
• Enhancing Feature-Specific Data Protection via Bayesian Coordinate Differential Privacy [55.357715095623554]
  Local Differential Privacy (LDP) offers strong privacy guarantees without requiring users to trust external parties. We propose a Bayesian framework, Bayesian Coordinate Differential Privacy (BCDP), that enables feature-specific privacy quantification.
  arXiv  Detail & Related papers  (2024-10-24T03:39:55Z)
• DePrompt: Desensitization and Evaluation of Personal Identifiable Information in Large Language Model Prompts [11.883785681042593]
  DePrompt is a desensitization protection and effectiveness evaluation framework for prompt. We integrate contextual attributes to define privacy types, achieving high-precision PII entity identification. Our framework is adaptable to prompts and can be extended to text usability-dependent scenarios.
  arXiv  Detail & Related papers  (2024-08-16T02:38:25Z)
• 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)
• 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)

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.