# Detecting Cognitive Signatures in Typing Behavior for Non-Intrusive Authorship Verification

arXiv: https://arxiv.org/abs/2603.00177 · HTML: https://mlsanity.com/paper/2603.00177/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 38 references that are in the map.
- First posted on arXiv 26 Feb 2026.

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

- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews](https://mlsanity.com/paper/2403.07183/) (2024)
- [Computer keyboard interaction as an indicator of early Parkinson's disease](https://mlsanity.com/paper/1604.08620/) (2016)
- [ScholaWrite: A Dataset of End-to-End Scholarly Writing Process](https://mlsanity.com/paper/2502.02904/) (2025)
- [Keystroke dynamics as signal for shallow syntactic parsing](https://mlsanity.com/paper/1610.03321/) (2016)
- [Adoption of Watermarking for Generative AI Systems in Practice and Implications under the new EU AI Act](https://mlsanity.com/paper/2503.18156/) (2025)
- [Detecting LLM-Assisted Academic Dishonesty using Keystroke Dynamics](https://mlsanity.com/paper/2511.12468/) (2025)
- [On the Insecurity of Keystroke-Based AI Authorship Detection: Timing-Forgery Attacks Against Motor-Signal Verification](https://mlsanity.com/paper/2601.17280/) (2026)
- [A critical analysis of cognitive load measurement methods for evaluating the usability of different types of interfaces: guidelines and framework for Human-Computer Interaction](https://mlsanity.com/paper/2402.11820/) (2024)
- [Uncertainty in Authorship: Why Perfect AI Detection Is Mathematically Impossible](https://mlsanity.com/paper/2509.11915/) (2025)

## Built on by (most cited first, 1 of 1)

- [Detecting LLM-Assisted Vietnamese Writing via Keystrokes under Behavioral Manipulation](https://mlsanity.com/paper/2610.07700/) (2026)

## Abstract (arXiv)

The proliferation of AI-generated text has intensified the need for reliable authorship verification, yet current output-based methods are increasingly unreliable. We observe that the ordinary typing interface captures rich cognitive signatures, measurable patterns in keystroke timing that reflect the planning, translating, and revising stages of genuine composition. Drawing on large-scale keystroke datasets comprising over 136 million events, we define the Cognitive Load Correlation (CLC) and show it distinguishes genuine composition from mechanical transcription. We present a non-intrusive verification framework that operates within existing writing interfaces, collecting only timing metadata to preserve privacy. Our analytical evaluation estimates 85 to 95 percent discrimination accuracy under stated assumptions, while limiting biometric leakage via evidence quantization. We analyze the adversarial robustness of cognitive signatures, showing they resist timing-forgery attacks that defeat motor-level authentication because the cognitive channel is entangled with semantic content. We conclude that reframing authorship verification as a human-computer interaction problem provides a privacy-preserving alternative to invasive surveillance.