InkShield: Writing Style Protection Against Unauthorized Handwriting Mimicry

2026-07-29

AI Summary

This work proposes an active defense mechanism tailored to protect handwritten styles from adversarial exploitation, wherein attackers could leverage publicly available handwriting samples and generative models to forge identities. The method applies imperceptible perturbations to reference images prior to release, carefully constraining these perturbations to stroke boundaries to preserve visual fidelity (LPIPS 0.0078) and textual legibility while steering generative models toward the stylistic characteristics of a decoy author. As the first protection scheme specifically designed for handwriting imitation, it significantly reduces the likelihood that the target author is ranked in the top-1 or top-5 by style classifiers on the IAM dataset—from 11.94% and 36.52% down to 2.03% and 8.79%, respectively—and demonstrates strong transferability across different generative architectures.

Abstract

Recent handwritten text generators can reproduce a writer's style from publicly available references, posing risks of document forgery and identity misuse. An attacker may use a publicly available handwritten note or signature sample to generate forged recommendation letters or authorization forms, leading to document fraud, identity misuse, and misleading decisions. However, existing protections against unauthorized image editing or synthesis transfer poorly to handwriting style mimicry. Designed for natural images with complex backgrounds, they often optimize perturbations over the whole image. For sparse handwriting images, such global perturbations become conspicuous in blank background regions and largely degrade the visual quality. In this work, we propose InkShield, a proactive writing-style defense that protects reference images before release. InkShield selects a decoy writer to define a style-displacement direction, optimizes perturbations with a frozen handwriting-generation surrogate, and confines them to ink-stroke edges to avoid conspicuous background artifacts. On IAM, the average Top-1/Top-5 rates at which generated samples are retrieved as the target writer by two independent writer evaluators decrease from 11.94%/36.52% to 2.03%/8.79%. Meanwhile, the protected references remain visually close to the originals (LPIPS 0.0078), and the generated text remains readable. InkShield also exhibits transferability to other handwriting generators. Overall, InkShield provides practical protection against unauthorized handwriting style mimicry.

Problem

• handwriting style mimicry
• document forgery
• identity misuse
• style protection
• unauthorized synthesis

Innovation

• handwriting style protection
• adversarial perturbation
• style mimicry defense
• ink-stroke constrained optimization
• decoy writer