Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attack

arXiv:2404.01907v1 Announce Type: cross
Abstract: With the development of large language models (LLMs), detecting whether text is generated by a machine becomes increasingly challenging in the face of malicious use cases like the spread of false information, protection of intellectual property, and prevention of academic plagiarism. While well-trained text detectors have demonstrated promising performance on unseen test data, recent research suggests that these detectors have vulnerabilities when dealing with adversarial attacks such as paraphrasing. In this paper, we propose a …

abstract academic adversarial arxiv cases cs.cl cs.cr cs.lg detection detectors development face false generated information intellectual property language language models large language large language models llms machine plagiarism prevention property protection text through type use cases