# LLM-Assisted Cheating Detection in Korean Language via Keystrokes

arXiv: https://arxiv.org/abs/2507.22956 · HTML: https://mlsanity.com/paper/2507.22956/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 53 references that are in the map.
- First posted on arXiv 29 Jul 2025.

## Builds on (most cited first, 10 of 10)

- [TypeNet: Deep Learning Keystroke Biometrics](https://mlsanity.com/paper/2101.05570/) (2021)
- [Synthesizing Human Gaze Feedback for Improved NLP Performance](https://mlsanity.com/paper/2302.05721/) (2023)
- [Keystroke dynamics as signal for shallow syntactic parsing](https://mlsanity.com/paper/1610.03321/) (2016)
- [TypeFormer: Transformers for Mobile Keystroke Biometrics](https://mlsanity.com/paper/2212.13075/) (2022)
- [Continuous Authentication Using One-class Classifiers and their Fusion](https://mlsanity.com/paper/1710.11075/) (2017)
- [Keystroke Dynamics: Concepts, Techniques, and Applications](https://mlsanity.com/paper/2303.04605/) (2023)
- [Keystroke Dynamics Against Academic Dishonesty in the Age of LLMs](https://mlsanity.com/paper/2406.15335/) (2024)
- [E-cheating Prevention Measures: Detection of Cheating at Online Examinations Using Deep Learning Approach -- A Case Study](https://mlsanity.com/paper/2101.09841/) (2021)
- [Spotting Fake Profiles in Social Networks via Keystroke Dynamics](https://mlsanity.com/paper/2311.06903/) (2023)
- [IEEE BigData 2023 Keystroke Verification Challenge (KVC)](https://mlsanity.com/paper/2401.16559/) (2024)

## Built on by (most cited first, 3 of 3)

- [On the Insecurity of Keystroke-Based AI Authorship Detection: Timing-Forgery Attacks Against Motor-Signal Verification](https://mlsanity.com/paper/2601.17280/) (2026)
- [Does AI Assistance Leave a Temporal Fingerprint? Detecting Overreliance in AI-Assisted Writing and Programming](https://mlsanity.com/paper/2609.17883/) (2026)
- [Detecting GPT-Assisted Writing Using Interpretable Stylometric Features](https://mlsanity.com/paper/2609.26687/) (2026)

## Abstract (arXiv)

This paper presents a keystroke-based framework for detecting LLM-assisted cheating in Korean, addressing key gaps in prior research regarding language coverage, cognitive context, and the granularity of LLM involvement. Our proposed dataset includes 69 participants who completed writing tasks under three conditions: Bona fide writing, paraphrasing ChatGPT responses, and transcribing ChatGPT responses. Each task spans six cognitive processes defined in Bloom's Taxonomy (remember, understand, apply, analyze, evaluate, and create). We extract interpretable temporal and rhythmic features and evaluate multiple classifiers under both Cognition-Aware and Cognition-Unaware settings. Temporal features perform well under Cognition-Aware evaluation scenarios, while rhythmic features generalize better under cross-cognition scenarios. Moreover, detecting bona fide and transcribed responses was easier than paraphrased ones for both the proposed models and human evaluators, with the models significantly outperforming the humans. Our findings affirm that keystroke dynamics facilitate reliable detection of LLM-assisted writing across varying cognitive demands and writing strategies, including paraphrasing and transcribing LLM-generated responses.