Keystroke dynamics models outperform text-only detectors for spotting LLM-assisted academic dishonesty in practical scenarios, though performance drops under adversarial conditions.
Feature-based detection of automated language models: tackling gpt-2, gpt-3 and grover.PeerJ Computer Science, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Detecting LLM-Assisted Academic Dishonesty using Keystroke Dynamics
Keystroke dynamics models outperform text-only detectors for spotting LLM-assisted academic dishonesty in practical scenarios, though performance drops under adversarial conditions.