自适应文本匿名化：通过提示优化学习隐私-效用权衡
Adaptive Text Anonymization: Learning Privacy-Utility Trade-offs via Prompt Optimization
AI总结：
本文提出自适应文本匿名化任务，通过提示优化框架自动构建匿名化指令，实现隐私与效用的动态平衡，优于现有方法且计算高效。
摘要：
文本匿名化是一个高度依赖上下文的问题：隐私保护与效用保持的平衡因数据领域、隐私目标和下游应用而异。现有方法依赖静态手动设计策略，缺乏灵活性且难以跨领域泛化。我们引入自适应文本匿名化任务，提出任务特定的提示优化框架，自动为语言模型构建匿名化指令，适应不同隐私目标、领域和下游使用模式。我们展示了涵盖五个不同领域、隐私约束和效用目标的数据集基准。在所有评估设置中，我们的框架在隐私-效用权衡上优于现有基线，计算高效且在开源语言模型上表现良好，与封闭源模型性能相当。此外，我们展示了该方法能发现探索隐私-效用权衡前沿不同点的新匿名化策略。
英文摘要：
Anonymizing textual documents is a highly context-sensitive problem: the appropriate balance between privacy protection and utility preservation varies with the data domain, privacy objectives, and downstream application. However, existing anonymization methods rely on static, manually designed strategies that lack the flexibility to adjust to diverse requirements and often fail to generalize across domains. We introduce adaptive text anonymization, a new task formulation in which anonymization strategies are automatically adapted to specific privacy-utility requirements. We propose a framework for task-specific prompt optimization that automatically constructs anonymization instructions for language models, enabling adaptation to different privacy goals, domains, and downstream usage patterns. To evaluate our approach, we present a benchmark spanning five datasets with diverse domains, privacy constraints, and utility objectives. Across all evaluated settings, our framework consistently achieves a better privacy-utility trade-off than existing baselines, while remaining computationally efficient and effective on open-source language models, with performance comparable to larger closed-source models. Additionally, we show that our method can discover novel anonymization strategies that explore different points along the privacy-utility trade-off frontier.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
