Large Language Models are Advanced Anonymizers

arXiv:2402.13846v1 Announce Type: cross
Abstract: Recent work in privacy research on large language models has shown that they achieve near human-level performance at inferring personal data from real-world online texts. With consistently increasing model capabilities, existing text anonymization methods are currently lacking behind regulatory requirements and adversarial threats. This raises the question of how individuals can effectively protect their personal data in sharing online texts. In this work, we take two steps to answer this question: We first present a …

abstract advanced adversarial anonymization arxiv capabilities cs.ai cs.cl cs.cr cs.lg data human language language models large language large language models near performance personal data privacy question raises regulatory requirements research text threats type work world