Skip to main content
Search

# Text Anonymization

2 related articles

Subscribe to updates
  1. arXiv

    AURA combines mask-reconstruct anonymization with adversarial screening to reach the lowest agentic re-identification counts among non-DP methods and recover 6.4 percentage points more contextual utility than a prior LLM anonymizer at comparable privacy

    The work introduces AURA (Anonymization with Utility-Retention Adaptation), an LLM-powered mask-reconstruct framework that decouples privacy localization from utility-preserving reconstruction and selects candidates through adversarial privacy and utility-retention checks; evaluated on real-user interview transcripts with re-identification attacks carried out by web-search agents, adaptive-scope AURA yields the lowest agentic re-identification counts under each of three attacker models among non-DP methods, and at matched scope and backbone it retains more contextual utility than the prior LLM anonymizer (+6.4 pp unit-grid recovery) at comparable privacy.

  2. Anonymization of Portuguese Clinical Notes Using Large Language Models and Quantum-Enhanced Hybrid Architectures: Comparative Evaluation Study

    This study built a gold-standard corpus of 1000 Portuguese outpatient clinical notes manually annotated by 5 trained researchers for 5 protected-entity categories (patient names, dates, identifiers, organizations, and geographic locations) and, on a held-out test set of 500 notes, compared two stand-alone LLMs (Llama-3.1-8B-instruct and Llama-3.3-70B-instruct) with two quantum-enhanced hybrid models (Dynex-QML with 8B and 70B base models, using QUBO formulations to transform the final attention layer into a global constraint satisfaction problem solved by neuromorphic quantum annealing); the quantum-enhanced Dynex-QML-70B achieved the highest macro-F1 of 0.855 (95% CI 0.823-0.880), above stand-alone Llama-3.3-70B (0.726), Dynex-QML-8B (0.733), and Llama-3.1-8B (0.

You’re all caught up