Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Text

• URL: http://arxiv.org/abs/2603.17217v1
• Date: Tue, 17 Mar 2026 23:46:15 GMT
• Title: Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Text
• Abstract summary: We develop an on-premise, LLM-driven substitution pipeline that anonymizes text.<n>We measure privacy, semantic utility, and trainability under privacy.<n>Our method attains state-of-the-art privacy, minimal topical drift, strong factual utility, and low trainability loss.
• Score: 0.42821598129654453
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Responsible use of AI demands that we protect sensitive information without undermining the usefulness of data, an imperative that has become acute in the age of large language models. We address this challenge with an on-premise, LLM-driven substitution pipeline that anonymizes text by replacing personally identifiable information (PII) with realistic, type-consistent surrogates. Executed entirely within organizational boundaries using local LLMs, the approach prevents data egress while preserving fluency and task-relevant semantics. We conduct a systematic, multi-metric, cross-technique evaluation on the Action-Based Conversation Dataset, benchmarking against industry standards (Microsoft Presidio and Google DLP) and a state-of-the-art approach (ZSTS, in redaction-only and redaction-plus-substitution variants). Our protocol jointly measures privacy, semantic utility, and trainability under privacy via a lifecycle-ready criterion obtained by fine-tuning a compact encoder (BERT+LoRA) on sanitized text. In addition, we assess agentic Q&A performance by inserting an on-premise anonymization layer before the answering LLM and evaluating the quality of its responses. This intermediate, type-preserving substitution stage ensures that no sensitive content is exposed to third-party APIs, enabling responsible deployment of Q\&A agents without compromising confidentiality. Our method attains state-of-the-art privacy, minimal topical drift, strong factual utility, and low trainability loss, outperforming rule-based approaches and named-entity recognition (NER) baselines and ZSTS variants on the combined privacy--utility--trainability frontier. These results show that local LLM substitution yields anonymized corpora that are both responsible to use and operationally valuable: safe for agentic pipelines and suitable for downstream fine-tuning with limited degradation.

Related papers

• 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)
• Need to Know: Contextual-Integrity-Grounded Query Rewriting for Privacy-Conscious LLM Delegation [50.614874098786515]
  We recast privacy preserving query rewriting under Contextual Integrity.<n>We propose a CI-guided reinforcement learning framework that converts essential and non-essential sensitive spans into verifiable optimization signals.<n> Experiments show that our learned rewriter achieves the best privacy-utility tradeoff, achieving up to +10.1 average utility over on-device baselines.
  arXiv  Detail & Related papers  (2026-06-02T14:28:28Z)
• It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs [73.46918128880786]
  Self-distillation framework that decouples information suppression from task resolution.<n>Self-distillation framework that decouples information suppression from task resolution.
  arXiv  Detail & Related papers  (2026-05-18T13:57:44Z)
• Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation [22.16117894083848]
  We introduce Privacy-Preserving Fine-Tuning (PPFT), a novel training pipeline that eliminates the need for transmitting raw prompt text.<n>Our approach operates in two stages: first, we train a client-side encoder together with a server-side projection module and LLM, enabling the server to condition on k-pooled prompt embeddings instead of raw text.<n>Extensive experiments on domain-specific and general benchmarks demonstrate that PPFT achieves a striking balance between privacy and utility.
  arXiv  Detail & Related papers  (2026-04-08T08:49:17Z)
• NeuroFilter: Privacy Guardrails for Conversational LLM Agents [50.75206727081996]
  This work addresses the computational challenge of enforcing privacy for agentic Large Language Models (LLMs)<n>NeuroFilter is a guardrail framework that operationalizes contextual integrity by mapping norm violations to simple directions in the model's activation space.<n>A comprehensive evaluation across over 150,000 interactions, covering models from 7B to 70B parameters, illustrates the strong performance of NeuroFilter.
  arXiv  Detail & Related papers  (2026-01-21T05:16:50Z)
• STaR: Sensitive Trajectory Regulation for Unlearning in Large Reasoning Models [12.133996629992318]
  We propose a parameter-free, inference-time unlearning framework that achieves robust privacy protection throughout the reasoning process.<n>Experiments on the R-TOFU benchmark demonstrate that STaR achieves comprehensive and stable unlearning with minimal utility loss.
  arXiv  Detail & Related papers  (2026-01-14T08:35:23Z)
• 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)
• Semantically-Aware LLM Agent to Enhance Privacy in Conversational AI Services [0.0]
  We present a semantically-aware privacy agent designed to safeguard sensitive PII data when using remote Large Language Models (LLMs)<n>Unlike prior work that often degrade response quality, our approach dynamically replaces sensitive PII entities in user prompts with semantically consistent pseudonyms.<n>Our results show that LOPSIDED reduces semantic utility errors by a factor of 5 compared to baseline techniques.
  arXiv  Detail & Related papers  (2025-10-30T21:34:23Z)
• PrivacyPAD: A Reinforcement Learning Framework for Dynamic Privacy-Aware Delegation [33.37227619820212]
  We introduce a novel reinforcement learning framework called PrivacyPAD to solve this problem.<n>Our framework trains an agent to dynamically route text chunks, learning a policy that optimally balances the trade-off between privacy leakage and task performance.<n>Our framework achieves a new state-of-the-art on the privacy-utility frontier.
  arXiv  Detail & Related papers  (2025-10-16T19:38:36Z)
• SynBench: A Benchmark for Differentially Private Text Generation [35.908455649647784]
  Data-driven decision support in high-stakes domains like healthcare and finance faces significant barriers to data sharing.<n>Recent generative AI models, such as large language models, have shown impressive performance in open-domain tasks.<n>But their adoption in sensitive environments remains limited by unpredictable behaviors and insufficient privacy-preserving datasets.
  arXiv  Detail & Related papers  (2025-09-18T03:57:50Z)
• The Double-edged Sword of LLM-based Data Reconstruction: Understanding and Mitigating Contextual Vulnerability in Word-level Differential Privacy Text Sanitization [53.51921540246166]
  We show that Language Large Models (LLMs) can exploit the contextual vulnerability of DP-sanitized texts.<n>Experiments uncover a double-edged sword effect of LLM reconstructions on privacy and utility.<n>We propose recommendations for using data reconstruction as a post-processing step.
  arXiv  Detail & Related papers  (2025-08-26T12:22:45Z)
• AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text [8.758843436588297]
  AgentStealth is a self-reinforcing language model for text anonymization.<n>We show that our method outperforms baselines in both anonymization effectiveness and utility.<n>Our lightweight design supports direct deployment on edge devices, avoiding cloud reliance and communication-based privacy risks.
  arXiv  Detail & Related papers  (2025-06-26T02:48:16Z)
• Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation [70.62656296780074]
  We propose AIDSAFE: Agentic Iterative Deliberation for Safety Reasoning, a novel data generation recipe.<n>A data refiner stage in AIDSAFE ensures high-quality outputs by eliminating repetitive, redundant, and deceptive thoughts.<n>Our evaluations demonstrate that AIDSAFE-generated CoTs achieve superior policy adherence and reasoning quality.
  arXiv  Detail & Related papers  (2025-05-27T21:34:40Z)
• Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning [58.57194301645823]
  Large language models (LLMs) are increasingly integrated into real-world personalized applications.<n>The valuable and often proprietary nature of the knowledge bases used in RAG introduces the risk of unauthorized usage by adversaries.<n>Existing methods that can be generalized as watermarking techniques to protect these knowledge bases typically involve poisoning or backdoor attacks.<n>We propose name for harmless' copyright protection of knowledge bases.
  arXiv  Detail & Related papers  (2025-02-10T09:15:56Z)
• 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)

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.