In this work, we address the problem of text anonymization where the goal is to prevent adversaries from correctly inferring private attributes of the author, while keeping the text utility, i.e., meaning and semantics. We propose IncogniText, a technique that anonymizes the text to mislead a potential adversary into predicting a wrong private attribute value. Our empirical evaluation shows a reduction of private attribute leakage by more than 90%. Finally, we demonstrate the maturity of IncogniText for real-world applications by distilling its anonymization capability into a set of LoRA parameters associated with an on-device model.

翻译：本文研究文本匿名化问题，其目标是在保持文本效用（即意义和语义）的同时，防止攻击者正确推断作者的私有属性。我们提出IncogniText技术，通过对文本进行匿名化处理，误导潜在攻击者预测错误的私有属性值。实证评估表明，该方法可将私有属性泄露降低90%以上。最后，我们通过将IncogniText的匿名化能力提炼为一组与设备端模型关联的LoRA参数，证明了该技术在实际应用中的成熟度。