AURA：面向智能体重识别的 LLM 文本匿名化框架

View PDF HTML (experimental)

Abstract:Agentic LLMs with web search change the threat model for text anonymization: weak contextual cues can become cross-referenceable evidence for re-identification, yet those same details also carry downstream analytic value of the text. Existing defenses either remove explicit identifiers, perturb text for formal privacy, or test rewritten text against non-web inference models, leaving underexplored the operating region between resistance to agentic web-search re-identification and utility retention. We introduce AURA (\textbf{A}nonymization with \textbf{U}tility-\textbf{R}etention \textbf{A}daptation), an LLM-powered \textit{mask-reconstruct} framework that decouples privacy localization from utility-preserving reconstruction and selects candidates with adversarial privacy and utility-retention checks. We evaluate AURA on real-user interview transcripts using re-identification attacks carried out by web-search agents, along with a utility evaluation based on interviewee-profile facts, codebook facts, and the joint contextual utility grid. Our results show that adaptive-scope AURA yields the lowest agentic re-identification counts under each of three attacker models among the non-DP methods, and that at matched scope and backbone, AURA's mask-reconstruct design retains more contextual utility than the prior LLM anonymizer (+6.4 pp unit-grid recovery) at comparable privacy. Source Code: this https URL

Comments:	40 pages, 10 figures
Subjects:	Cryptography and Security (cs.CR); Computation and Language (cs.CL)
Cite as:	arXiv:2605.30848 [cs.CR]
	(or arXiv:2605.30848v3 [cs.CR] for this version)
	https://doi.org/10.48550/arXiv.2605.30848 arXiv-issued DOI via DataCite

Submission history

From: Ziwen Li [view email]
[v1] Fri, 29 May 2026 05:12:39 UTC (1,032 KB)
[v2] Mon, 1 Jun 2026 17:13:40 UTC (1,032 KB)
[v3] Thu, 1 Oct 2026 21:15:17 UTC (1,022 KB)