Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

David Condrey

TL;DR

It is concluded that reframing authorship verification as a human-computer interaction problem provides a privacy-preserving alternative to invasive surveillance.

Abstract

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.

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

TL;DR

It is concluded that reframing authorship verification as a human-computer interaction problem provides a privacy-preserving alternative to invasive surveillance.

Abstract

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.
Paper Structure (31 sections, 1 equation, 3 figures, 2 tables)

This paper contains 31 sections, 1 equation, 3 figures, 2 tables.

Table of Contents

  1. INTRODUCTION
  2. BACKGROUND AND RELATED WORK
  3. Cognitive Process Theory of Writing
  4. Keystroke Dynamics as a Behavioral Signal
  5. Cognitive Load Measurement in HCI
  6. Ethical Considerations in Behavioral Monitoring
  7. COGNITIVE SIGNATURES IN TYPING
  8. The Composition Signature
  9. Planning phases.
  10. Translating phases.
  11. Revision phases.
  12. The Cognitive Load Correlation
  13. Empirical Grounding
  14. Visualizing Cognitive Signatures
  15. NON-INTRUSIVE VERIFICATION FRAMEWORK
  16. ...and 16 more sections

Figures (3)

  • Figure 1: Cognitive signature timeline. (a) Genuine composition exhibits high variance across several orders of magnitude, with planning spikes exceeding 1,000 ms. (b) Transcription remains tightly bounded around the motor baseline. Logarithmic scaling reveals the non-stationary nature of composition vs. the stationary motor signal of transcription.
  • Figure 2: System architecture showing the transformation of keystroke events into verifiable process evidence.
  • Figure 3: Modeled privacy-utility tradeoff. Accuracy curve is derived from published EER data at varying clock resolutions KillourhyMaxion2008; leakage curve is estimated from the biometric entropy of the Aalto 136M dataset Dhakal2018. Both curves are analytical projections, not empirical measurements from this study.