由推理攻击引导的真实文本脱敏
Truthful Text Sanitization Guided by Inference Attacks
AI总结:
针对文本脱敏中隐私保护与效用保留的平衡难题,提出基于泛化、结合LLM候选生成排序与推理攻击评估的两阶段方法,搭配新型无标注评估指标,在基准上实现效用提升且重识别风险增幅极小,保真性优于现有方法。
摘要:
文本脱敏旨在重写文档的部分内容以防止个人信息泄露。文本脱敏的核心挑战是在隐私保护(避免个人信息泄露)与效用保留(尽可能保留文档原始内容)之间取得平衡。为此,我们提出了一种基于泛化的新型文本脱敏方法,泛化指的是更宽泛但仍具信息量的术语,能够涵盖原始文本片段的语义内容。该方法依赖经过指令微调的大语言模型(LLM),分为两个阶段。给定包含表达个人可识别信息(PII)文本片段的文档,首先调用LLM为每个文本片段生成保真性替换候选,并根据其抽象程度对这些候选进行排序。随后,通过使用LLM开展推理攻击,评估这些候选的隐私保护能力。最终,系统会选择经证实能够抵御这些攻击且信息量最高的替换候选。这一两阶段流程生成的替换内容可有效平衡隐私与效用。我们还提出了无需人工标注文档即可评估这两个维度的新型指标。在Text Anonymization Benchmark(文本匿名化基准)上的结果表明,采用Mistral 7B Instruct实现的所提方法提升了效用,与完全抑制原始文本片段相比,重识别风险仅出现边际(<1个百分点)上升。此外,研究证明该方法比Microsoft Presidio的合成替换等现有方法更具保真性。
英文摘要:
Text sanitization aims to rewrite parts of a document to prevent disclosure of personal information. The central challenge of text sanitization is to strike a balance between privacy protection (avoiding the leakage of personal information) and utility preservation (retaining as much as possible of the document's original content). To this end, we introduce a novel text sanitization method based on generalizations, that is, broader but still informative terms that subsume the semantic content of the original text spans. The approach relies on the use of instruction-tuned large language models (LLMs) and is divided into two stages. Given a document including text spans expressing personally identifiable information (PII), the LLM is first applied to obtain truth-preserving replacement candidates for each text span and rank those according to their abstraction level. Those candidates are then evaluated for their ability to protect privacy by conducting inference attacks with the LLM. Finally, the system selects the most informative replacement candidate shown to be resistant to those attacks. This two-stage process produces replacements that effectively balance privacy and utility. We also present novel metrics to evaluate these two aspects without needing to manually annotate documents. Results on the Text Anonymization Benchmark show that the proposed approach, implemented with Mistral 7B Instruct, leads to enhanced utility, with only a marginal (< 1 p.p.) increase in re-identification risk compared to fully suppressing the original spans. Furthermore, our approach is shown to be more truth-preserving than existing methods such as Microsoft Presidio's synthetic replacements.
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。