Metraipolis › archive › dc_b52f302f2cb1

Detecting LLM-Assisted Vietnamese Writing via Keystrokes under Behavioral Manipulation — arXiv:2610.07700

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07700
License (as archived)
CC0-1.0
Archived
2026-10-07T11:23:09.693Z
SHA-256 of the archived text
9ca9ed2a52e223b17cec493141c66f7ac334d6a44956a8e01267bdb463454358
Stable URL of this page
https://metraipolis.com/documento/dc_b52f302f2cb1

How to cite

Detecting LLM-Assisted Vietnamese Writing via Keystrokes under Behavioral Manipulation — arXiv:2610.07700 — arXiv (en), https://arxiv.org/abs/2610.07700 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b52f302f2cb1 (Metraipolis archive dc_b52f302f2cb1, sha256 9ca9ed2a52e223b17cec493141c66f7ac334d6a44956a8e01267bdb463454358)
BibTeX
@misc{dcb52f302f2cb1,
  title = {Detecting LLM-Assisted Vietnamese Writing via Keystrokes under Behavioral Manipulation — arXiv:2610.07700},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07700},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b52f302f2cb1; sha256 9ca9ed2a52e223b17cec493141c66f7ac334d6a44956a8e01267bdb463454358},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07700. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study the robustness of keystroke dynamics for detecting large language model (LLM)-assisted writing. We introduce a Vietnamese keystroke dataset capturing realistic writing modes, including bona fide composition, transcription, and paraphrasing. We also define a behaviorally grounded threat model in which users deliberately alter typing patterns. To implement the threat model, we create behaviorally manipulated variants of the data designed to evade keystroke-based detection. We evaluate four keystroke modeling approaches: temporal and rhythmic representations, and sequential representations modeled with a one-dimensional convolutional neural network (1D-CNN) and TypeNet, under user-independent and context-independent settings. The results show that sequential models outperform feature-based approaches in most cases and that keystroke signals encode discriminative information about the writing process. However, detection is not uniformly robust: transcription is reliably identified, while paraphrasing and adversarially manipulated samples are frequently misclassified as bona fide when not explicitly modeled. To address this, we incorporate adversarial training using behaviorally manipulated data, which substantially improves separability and robustness. These results suggest that keystroke-based detection depends critically on exposure to diverse writing behaviors, and that strong performance under limited conditions does not generalize to realistic or adversarial settings without targeted modeling.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2610.07700 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T11:15:39.426Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).