Year: 2026
Type: conference-paper
Abstract: As LLMs rapidly advance and enter realworld use, their privacy implications are increasingly important.We study an authorship de-anonymization threat: using LLMs to link anonymous documents to their authors, potentially compromising settings such as double-blind peer review.We propose De-Anonymization at Scale (DAS), a largelanguage-model-based method for attributing authorship among tens of thousands of candidate texts.DAS uses a sequential progression strategy: it randomly partitions the candidate corpus into fixed-size groups, prompts an LLM to select the text most likely written by the same author as a query text, and iteratively requeries the surviving candidates to produce a ranked top-k list.To make this practical at scale, DAS adds a dense-retrieval prefilter to shrink the search space and a majority-voting-style aggregation over multiple independent runs to improve robustness and ranking precision.Experiments on anonymized review data show DAS can recover same-author texts from pools of tens of thousands with accuracy well above chance, demonstrating a realistic privacy risk for anonymous platforms.On standard authorship benchmarks (Enron emails and blog posts), DAS also improves both accuracy and scalability over prior approaches, highlighting a new LLM-enabled de-anonymization vulnerability.
Authors: Lirui Zhang, Huishuai Zhang
Institutions: Beihang University, Peking University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166842613