TOPFORMER: Topology-Aware Authorship Attribution of Deepfake Texts with Diverse Writing Styles

arXiv:2309.12934v2 Announce Type: replace
Abstract: Recent advances in Large Language Models (LLMs) have enabled the generation of open-ended high-quality texts, that are non-trivial to distinguish from human-written texts. We refer to such LLM-generated texts as deepfake texts. There are currently over 72K text generation models in the huggingface model repo. As such, users with malicious intent can easily use these open-sourced LLMs to generate harmful texts and dis/misinformation at scale. To mitigate this problem, a computational method to determine if …

abstract advances arxiv attribution authorship cs.cl deepfake diverse generated huggingface human language language models large language large language models llm llms quality text text generation topology type writing