Preserving privacy without compromising accuracy: Machine unlearning for handwritten text recognition

Download PDF
Open Webpage

Lei Kang, Xuanshuo Fu, Lluís Gómez, Alicia Fornés, Ernest Valveny, Dimosthenis Karatzas

Published: 01 Jan 2026, Last Modified: 14 Nov 2025Pattern Recognit. 2026EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Encoder-only Transformer baseline for handwriting text recognition (HTR).•Added writer-style head tracks & controls user-identifiable memorization.•Neural-activation pruning removes writer clues while preserving HTR accuracy.•Writer-ID Confusion (WIC) enforces uniform IDs, boosting efficient machine unlearning.•Membership-inference tests confirm privacy gains without costly retraining.