Towards Fine-grained and Robust Detection of Human-AI Co-authorship

A new arXiv paper (arXiv:2611.01427v1) proposes a discrete-class text provenance detection framework that separates surface-level AI polishing from AI-driven changes to discourse structure, aiming to give finer-grained signals of AI involvement than one-dimensional human-AI co-authorship scores. The authors report that adversarial paraphrasing substantially degrades detectors trained only on benign data, and that augmenting training data with paraphrases from a state-of-the-art paraphrasing attack model yields consistent robustness gains and good cross-generator transferability across multiple datasets and generation models.

arXiv:2611.01427v1 Announce Type: new Abstract: The widespread adoption of large language models LLMs is reshaping how textual content is produced, complicating text provenance, and raising concerns for misinformation, plagiarism, and intellectual property. While prior work on AI-generated text detection has progressed, one-dimensional human-AI co-authorship scores lack signals directly relevant to AI involvement''. It remains unclear how adversarial paraphrasing distorts detection signals. In this work, we formulate a discrete-class text provenance detection framework. This framework allows an abstraction of realistic co-authorship scenarios into distinct degrees of AI involvement, differentiating the AI polishing on the surface level from the AI updating the discourse structures. This framework reveals the mechanisms of how adversarial paraphrasing blurs the decision boundaries for co-authorship detectors. To improve robustness of the detectors, we augment training data with adversarial paraphrases generated by the state-of-the-art paraphrasing attack model, exposing detectors to challenging meaning-preserving rewrites. Extensive experiments across multiple datasets and generation models demonstrate that adversarial paraphrasing substantially degrades detectors trained only on benign data, while adversarial data augmentation leads to consistent robustness gains and good cross-generator transferability. Overall, our findings highlight the value of discrete-class formulation and principled data augmentation for building reliable detectors of human-AI co-authorship.