AI RESEARCH
De-Anonymization at Scale via Tournament-Style Attribution
arXiv CS.LG
•
ArXi:2601.12407v2 Announce Type: replace-cross As LLMs rapidly advance and enter real-world 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 large language model-based method for attributing authorship among tens of thousands of candidate texts.