# Hijacking Text Heritage: Hiding the Human Signature through Homoglyphic Substitution

arXiv: https://arxiv.org/abs/2604.10271 · HTML: https://mlsanity.com/paper/2604.10271/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 34 references that are in the map.
- First posted on arXiv 11 Apr 2026.

## Builds on (most cited first, 14 of 14)

- [RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors](https://mlsanity.com/paper/2405.07940/) (2024)
- [Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges](https://mlsanity.com/paper/2408.08946/) (2024)
- [Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective](https://mlsanity.com/paper/2210.10488/) (2022)
- [Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attacks](https://mlsanity.com/paper/2402.11638/) (2024)
- [Data Poisoning in Deep Learning: A Survey](https://mlsanity.com/paper/2503.22759/) (2025)
- [Authorship Obfuscation in Multilingual Machine-Generated Text Detection](https://mlsanity.com/paper/2401.07867/) (2024)
- [Large-scale online deanonymization with LLMs](https://mlsanity.com/paper/2602.16800/) (2026)
- [SilverSpeak: Evading AI-Generated Text Detectors using Homoglyphs](https://mlsanity.com/paper/2406.11239/) (2024)
- [Data-Driven Mitigation of Adversarial Text Perturbation](https://mlsanity.com/paper/2202.09483/) (2022)
- [DAMASHA: Detecting AI in Mixed Adversarial Texts via Segmentation with Human-interpretable Attribution](https://mlsanity.com/paper/2512.04838/) (2025)
- [Unveiling Unicode's Unseen Underpinnings in Undermining Authorship Attribution](https://mlsanity.com/paper/2508.15840/) (2025)
- [Tuning for TraceTarnish: Techniques, Trends, and Testing Tangible Traits](https://mlsanity.com/paper/2512.03465/) (2025)
- [Style Attack Disguise: When Fonts Become a Camouflage for Adversarial Intent](https://mlsanity.com/paper/2510.19641/) (2025)
- [StegoStylo: Squelching Stylometric Scrutiny through Steganographic Stitching](https://mlsanity.com/paper/2601.09056/) (2026)

## Abstract (arXiv)

In what way could a data breach involving government-issued IDs such as passports, driver's licenses, etc., rival a random voluntary disclosure on a nondescript social-media platform? At first glance, the former appears more significant, and that is a valid assessment. The disclosed data could contain an individual's date of birth and address; for all intents and purposes, a leak of that data would be disastrous. Given the threat, the latter scenario involving an innocuous online post seems comparatively harmless -- or does it? From that post and others like it, a forensic linguist could stylometrically uncover equivalent pieces of information, estimating an age range for the author (adolescent or adult) and narrowing down their geographical location (specific country). While not an exact science -- the determinations are statistical -- stylometry can reveal comparable, though noticeably diluted, information about an individual. To prevent an ID from being breached, simply sharing it as little as possible suffices. Preventing the leakage of personal information from written text requires a more complex solution: adversarial stylometry. In this paper, we explore how performing homoglyph substitution -- the replacement of characters with visually similar alternatives (e.g., "h" texttt[U+0068] rightarrow "h" texttt[U+04BB]) -- on text can degrade stylometric systems.