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.
| Comments: | 7 pages |
| Subjects: | Cryptography and Security (cs.CR); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG) |
| MSC classes: | 68T10, 91E45, 68U35 |
| ACM classes: | K.6.5; H.5.2; I.5.4 |
| Cite as: | arXiv:2603.00177 [cs.CR] |
| (or arXiv:2603.00177v2 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2603.00177 arXiv-issued DOI via DataCite |
From: David L. Condrey [view email]
[v1]
Thu, 26 Feb 2026 20:02:55 UTC (18 KB)
[v2]
Fri, 24 Apr 2026 06:26:04 UTC (18 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。