Hijacking Text Heritage: Hiding the Human Signature through Homoglyphic Substitution

• URL: http://arxiv.org/abs/2604.10271v1
• Date: Sat, 11 Apr 2026 16:27:32 GMT
• Title: Hijacking Text Heritage: Hiding the Human Signature through Homoglyphic Substitution
• Abstract summary: A data breach involving government-issued IDs could rival a random voluntary disclosure on a nondescript social-media platform.<n>To prevent an ID from being breached, simply sharing it as little as possible suffices.<n>In this paper, we explore how performing homoglyph substitution--the replacement of characters with visually similar alternatives--can degrade stylometric systems.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• I Am No One: Style-Aware Paraphrasing for Text Anonymization [0.5874782446136914]
  Authorship attribution models can re-identify users from seemingly anonymized text by exploiting stable stylistic fingerprints.<n>We propose a style-aware, prompt-driven anonymization approach that uses pretrained large language models to construct compact stylistic profiles.<n>Our approach reduces authorship attribution F1 by 60-70% while maintaining content quality and readability.
  arXiv  Detail & Related papers  (2026-09-11T02:07:26Z)
• StegoStylo: Squelching Stylometric Scrutiny through Steganographic Stitching [0.0]
  Stylometry supports copyright and plagiarism investigations, aids detection of harmful content, and provides historical context for literary works.<n>Stylometry is employed as a tool for authorship verification--confirming whether a text truly originates from a claimed author--it can also be weaponized for malicious purposes.<n>This paper explores how adversarial stylometry combined with steganography can counteract stylometric analysis.
  arXiv  Detail & Related papers  (2026-01-14T00:49:20Z)
• A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage [77.83757117924995]
  We propose a new framework that evaluates re-identification attacks to quantify individual privacy risks upon data release.<n>Our approach shows that seemingly innocuous auxiliary information can be used to infer sensitive attributes like age or substance use history from sanitized data.
  arXiv  Detail & Related papers  (2025-04-28T01:16:27Z)
• IDT: Dual-Task Adversarial Attacks for Privacy Protection [8.312362092693377]
  Methods to protect privacy can involve using representations inside models that are not to detect sensitive attributes. We propose IDT, a method that analyses predictions made by auxiliary and interpretable models to identify which tokens are important to change. We evaluate different datasets for NLP suitable for different tasks.
  arXiv  Detail & Related papers  (2024-06-28T04:14:35Z)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)
• Exploit the Leak: Understanding Risks in Biometric Matchers [0.0]
  In a biometric authentication or identification system, the matcher compares a stored and a fresh template to determine whether there is a match. For better compliance with privacy legislation, the matcher can be built upon a privacy-preserving distance. This paper provides an analysis of information leakage during distance evaluation.
  arXiv  Detail & Related papers  (2023-07-25T17:29:32Z)
• Unsupervised Text Deidentification [101.2219634341714]
  We propose an unsupervised deidentification method that masks words that leak personally-identifying information. Motivated by K-anonymity based privacy, we generate redactions that ensure a minimum reidentification rank.
  arXiv  Detail & Related papers  (2022-10-20T18:54:39Z)
• FedForgery: Generalized Face Forgery Detection with Residual Federated Learning [87.746829550726]
  Existing face forgery detection methods directly utilize the obtained public shared or centralized data for training. The paper proposes a novel generalized residual Federated learning for face Forgery detection (FedForgery) Experiments conducted on publicly available face forgery detection datasets prove the superior performance of the proposed FedForgery.
  arXiv  Detail & Related papers  (2022-10-18T03:32:18Z)
• PART: Pre-trained Authorship Representation Transformer [52.623051272843426]
  Authors writing documents imprint identifying information within their texts.<n>Previous works use hand-crafted features or classification tasks to train their authorship models.<n>We propose a contrastively trained model fit to learn textbfauthorship embeddings instead of semantics.
  arXiv  Detail & Related papers  (2022-09-30T11:08:39Z)
• RealGait: Gait Recognition for Person Re-Identification [79.67088297584762]
  We construct a new gait dataset by extracting silhouettes from an existing video person re-identification challenge which consists of 1,404 persons walking in an unconstrained manner. Our results suggest that recognizing people by their gait in real surveillance scenarios is feasible and the underlying gait pattern is probably the true reason why video person re-idenfification works in practice.
  arXiv  Detail & Related papers  (2022-01-13T06:30:56Z)
• Protecting gender and identity with disentangled speech representations [49.00162808063399]
  We show that protecting gender information in speech is more effective than modelling speaker-identity information. We present a novel way to encode gender information and disentangle two sensitive biometric identifiers.
  arXiv  Detail & Related papers  (2021-04-22T13:31:41Z)
• A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation [50.55448707570669]
  We propose a novel token-level, reference-free hallucination detection task and an associated annotated dataset named HaDes. To create this dataset, we first perturb a large number of text segments extracted from English language Wikipedia, and then verify these with crowd-sourced annotations.
  arXiv  Detail & Related papers  (2021-04-18T04:09:48Z)
• PhishGAN: Data Augmentation and Identification of Homoglpyh Attacks [0.0]
  Homoglyph attacks are a common technique used by hackers to conduct phishing. Domain names or links that are visually similar to actual ones are created via punycode to obfuscate the attack. Here, we show how a conditional Generative Adversarial Network (GAN), PhishGAN, can be used to generate images of hieroglyphs.
  arXiv  Detail & Related papers  (2020-06-24T13:59:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.