一作ACL 2026Poster· Natural Language Processing
De-Anonymization at Scale via Tournament-Style Attribution
Lirui Zhang · Huishuai Zhang
摘要
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-Anony...