IDP-Bench: Benchmarking ability of LLMs to protect personal information in interdependent privacy contexts

• URL: http://arxiv.org/abs/2606.09908v1
• Date: Sat, 06 Jun 2026 07:59:08 GMT
• Title: IDP-Bench: Benchmarking ability of LLMs to protect personal information in interdependent privacy contexts
• Abstract summary: 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.
• Score: 15.026169063578697
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are becoming widely deployed as personal AI assistants with access to sensitive user data, making privacy a major challenge for their design and evaluation. Prior work focuses mainly on individual-level risks, overlooking \textbf{interdependent privacy (IDP)}--where one person's data may be revealed by others without their knowledge or consent. We address this gap by introducing \textbf{IDP-Bench}: the first LLM benchmark for IDP scenarios, grounded in the Contextual Integrity (CI) framework. We evaluate eight open-source LLMs on their understanding of IDP scenarios across three levels of IDP reasoning using two LLM judges. Results show strong co-ownership recognition (6/8 models exceed 90\%) but persistent weaknesses in identifying CI parameters (information attribute, primary subject) and IDP-specific parameters such as secondary subjects, where 7/8 models score below 74\%. Models also struggle to judge sharing appropriateness (5/8 scoring below 77\%). While the ability to judge the appropriateness of sharing improves with scale, performance tends to decline in smaller models, and prompt sensitivity remains high on IDP-specific questions--highlighting the need for more targeted study of IDP in LLM privacy research. Data \& code available \href{https://github.com/tisl-lab/Interdependent_Privacy_Bench}{here}.

Related papers

• Beyond Direct Identifiers: Probabilistic Privacy Risk Estimation for Privacy-Conscious LLM Query Delegation [20.31515213689976]
  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.
  arXiv  Detail & Related papers  (2026-08-10T05:38:28Z)
• PANOPTICON: A PII-Based Assemblage of Naturalistic Output Tokens for Investigating Privacy Leakage Within LLM Context Window [0.49703640686206074]
  Large Language Models (LLMs) are capable of generalizing human language for the completion of never-before-seen tasks.<n>These tasks often require the insertion of Personally Identifiable Information (PII), strings of information that uniquely identify some individual, raising privacy concerns.<n>We introduce the PANOPTICON pipeline and dataset, containing PII spans from 9,674 publicly available synthetic user profiles.
  arXiv  Detail & Related papers  (2026-07-17T17:23:39Z)
• Seeing Without Exposing: Adaptive Privacy Control for Open-World, Context-Hungry MLLMs [61.80513991207956]
  We propose Anchored Privacy Drifting (APD) to tackle privacy challenges in MLLMs.<n>APD drifts privacy-sensitive elements toward semantically equivalent alternatives while anchoring contextual cues to the source image.<n>We show that our method achieves balanced improvements in both privacy sanitization and content retention.
  arXiv  Detail & Related papers  (2026-06-05T11:41:39Z)
• MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models [14.942122955210436]
  Modern Vision-Language Models (VLMs) demonstrate sophisticated reasoning, escalating privacy risks.<n>Current privacy benchmarks are structurally insufficient for this new threat.<n>We propose textbfMultiPriv, the first benchmark designed to systematically evaluate individual-level privacy reasoning.
  arXiv  Detail & Related papers  (2025-11-21T04:33:11Z)
• 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)
• Do LLMs Recognize Your Latent Preferences? A Benchmark for Latent Information Discovery in Personalized Interaction [40.857161437572465]
  We introduce a benchmark for evaluating latent information discovery in personalized interaction.<n>The benchmark spans three progressively realistic settings: the classic 20 Questions game, Personalized Question Answering, and Personalized Text Summarization.<n>Our results reveal that while LLMs can indeed surface latent information through dialogue, their success varies dramatically with context.
  arXiv  Detail & Related papers  (2025-10-20T03:58:49Z)
• 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)
• IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
  IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
  arXiv  Detail & Related papers  (2025-05-23T09:37:52Z)
• Federated Fine-Tuning of LLMs: Framework Comparison and Research Directions [59.5243730853157]
  Federated learning (FL) provides a privacy-preserving solution for fine-tuning pre-trained large language models (LLMs) using distributed private datasets.<n>This article conducts a comparative analysis of three advanced federated LLM (FedLLM) frameworks that integrate knowledge distillation (KD) and split learning (SL) to mitigate these issues.
  arXiv  Detail & Related papers  (2025-01-08T11:37:06Z)
• Robust Utility-Preserving Text Anonymization Based on Large Language Models [80.5266278002083]
  Anonymizing text that contains sensitive information is crucial for a wide range of applications.<n>Existing techniques face the emerging challenges of the re-identification ability of large language models.<n>We propose a framework composed of three key components: a privacy evaluator, a utility evaluator, and an optimization component.
  arXiv  Detail & Related papers  (2024-07-16T14:28:56Z)
• Noisy Neighbors: Efficient membership inference attacks against LLMs [2.666596421430287]
  This paper introduces an efficient methodology that generates textitnoisy neighbors for a target sample by adding noise in the embedding space. Our findings demonstrate that this approach closely matches the effectiveness of employing shadow models, showing its usability in practical privacy auditing scenarios.
  arXiv  Detail & Related papers  (2024-06-24T12:02:20Z)
• 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)

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.