Local Language Models for Context-Aware Adaptive Anonymization of Sensitive Text

• URL: http://arxiv.org/abs/2601.14683v1
• Date: Wed, 21 Jan 2026 05:59:56 GMT
• Title: Local Language Models for Context-Aware Adaptive Anonymization of Sensitive Text
• Authors: Aisvarya Adeseye, Jouni Isoaho, Seppo Virtanen, Mohammad Tahir,
• Abstract summary: This study uses local LLMs to build a reliable, repeatable, and context-aware anonymization process.<n>We introduce a Structured Framework for Adaptive Anonymizer (SFAA) that includes three steps: detection, classification, and adaptive anonymization.
• Score: 0.7349727826230863
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Qualitative research often contains personal, contextual, and organizational details that pose privacy risks if not handled appropriately. Manual anonymization is time-consuming, inconsistent, and frequently omits critical identifiers. Existing automated tools tend to rely on pattern matching or fixed rules, which fail to capture context and may alter the meaning of the data. This study uses local LLMs to build a reliable, repeatable, and context-aware anonymization process for detecting and anonymizing sensitive data in qualitative transcripts. We introduce a Structured Framework for Adaptive Anonymizer (SFAA) that includes three steps: detection, classification, and adaptive anonymization. The SFAA incorporates four anonymization strategies: rule-based substitution, context-aware rewriting, generalization, and suppression. These strategies are applied based on the identifier type and the risk level. The identifiers handled by the SFAA are guided by major international privacy and research ethics standards, including the GDPR, HIPAA, and OECD guidelines. This study followed a dual-method evaluation that combined manual and LLM-assisted processing. Two case studies were used to support the evaluation. The first includes 82 face-to-face interviews on gamification in organizations. The second involves 93 machine-led interviews using an AI-powered interviewer to test LLM awareness and workplace privacy. Two local models, LLaMA and Phi were used to evaluate the performance of the proposed framework. The results indicate that the LLMs found more sensitive data than a human reviewer. Phi outperformed LLaMA in finding sensitive data, but made slightly more errors. Phi was able to find over 91% of the sensitive data and 94.8% kept the same sentiment as the original text, which means it was very accurate, hence, it does not affect the analysis of the qualitative data.

Related papers

• RAT-Bench: A Comprehensive Benchmark for Text Anonymization [8.64925947747086]
  We introduce RAT-Bench, a benchmark for text anonymization tools based on re-identification risk.<n>We generate synthetic text containing various direct and indirect identifiers across domains, languages, and difficulty levels.<n>We find that, while capabilities vary widely, even the best tools are far from perfect in particular when direct identifiers are not written in standard ways.
  arXiv  Detail & Related papers  (2026-02-13T10:41:44Z)
• CAPID: Context-Aware PII Detection for Question-Answering Systems [2.538582648751871]
  We propose CAPID, a practical approach that fine-tunes a locally owned small language model (SLM) that filters sensitive information before it is passed to LLMs for QA.<n>Existing datasets do not capture the context-dependent relevance of PII needed to train such a model effectively.<n>Our experiments show that relevance-aware PII detection with a fine-tuned SLM substantially outperforms existing baselines in span, relevance and type accuracy.
  arXiv  Detail & Related papers  (2026-02-10T18:41:31Z)
• 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)
• VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection [55.957275374847484]
  VulAgent is a multi-agent vulnerability detection framework based on hypothesis validation.<n>It implements a semantics-sensitive, multi-view detection pipeline, each aligned to a specific analysis perspective.<n>On average, VulAgent improves overall accuracy by 6.6%, increases the correct identification rate of vulnerable--fixed code pairs by up to 450%, and reduces the false positive rate by about 36%.
  arXiv  Detail & Related papers  (2025-09-15T02:25:38Z)
• 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)
• Self-Refining Language Model Anonymizers via Adversarial Distillation [48.280759014096354]
  We introduce SElf-refining Anonymization with Language model (SEAL)<n>SEAL is a novel distillation framework for training small language models (SLMs) to perform effective anonymization without relying on external models at inference time.<n>Experiments on SynthPAI, a dataset of synthetic personal profiles and text comments, demonstrate that SLMs trained with SEAL achieve substantial improvements in anonymization capabilities.
  arXiv  Detail & Related papers  (2025-06-02T08:21:27Z)
• Can Large Language Models Really Recognize Your Name? [23.4365383606717]
  We show that modern large language models (LLMs) regularly overlook human names even in short text snippets due to ambiguous contexts.<n>We propose AMBENCH, a benchmark dataset of seemingly ambiguous human names.
  arXiv  Detail & Related papers  (2025-05-20T16:05:05Z)
• Automated Profile Inference with Language Model Agents [67.32226960040514]
  We study a new threat that LLMs pose to online pseudonymity, called automated profile inference.<n>An adversary can instruct LLMs to automatically scrape and extract sensitive personal attributes from publicly visible user activities on pseudonymous platforms.<n>We introduce an automated profiling framework called AutoProfiler to assess the feasibility of such threats in real-world scenarios.
  arXiv  Detail & Related papers  (2025-05-18T13:05:17Z)
• Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models [52.439289085318634]
  We show how to identify training data known to proprietary large language models (LLMs) by using information-guided probes.<n>Our work builds on a key observation: text passages with high surprisal are good search material for memorization probes.
  arXiv  Detail & Related papers  (2025-03-15T10:19:15Z)
• 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)
• ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks [91.55895047448249]
  This paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases. We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets. Our generated data is human-readable and useful to trigger hallucination in large language models.
  arXiv  Detail & Related papers  (2023-10-19T06:37:32Z)
• Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
  We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
  arXiv  Detail & Related papers  (2023-06-23T17:59:09Z)
• No Intruder, no Validity: Evaluation Criteria for Privacy-Preserving Text Anonymization [0.48733623015338234]
  We argue that researchers and practitioners developing automated text anonymization systems should carefully assess whether their evaluation methods truly reflect the system's ability to protect individuals from being re-identified. We propose TILD, a set of evaluation criteria that comprises an anonymization method's technical performance, the information loss resulting from its anonymization, and the human ability to de-anonymize redacted documents.
  arXiv  Detail & Related papers  (2021-03-16T18:18:29Z)

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.