Explainability-Driven Incremental Image Anonymization
Rami Haffar(a),(*), David Sánchez(a), Younas Khan(a), Josep Domingo-Ferrer(a)
Transactions on Data Privacy 18:3 (2025) 135 - 155
Abstract, PDF
(a) Universitat Rovira i Virgili, Department of Computer Engineering and Mathematics, CYBERCAT-Center for Cybersecurity Research of Catalonia, Av. Països Catalans 26, 43007 Tarragona, Catalonia.
e-mail:rami.haffar @urv.cat; david.sanchez @urv.cat; younas.khan @urv.cat; josep.domingo @urv.cat
|
Abstract
Privacy regulations require that images depicting humans be anonymized before they are publicly released or shared for secondary use. However, current image anonymization methods significantly degrade the analytical utility of protected images. This paper addresses the challenge of balancing privacy protection and utility preservation in image anonymization. We propose a general disclosure risk-aware anonymization framework that leverages explainability techniques to target identity-revealing features in images. Contrary to conventional methods, which uniformly perturb all image pixels, our proposal focuses on perturbing the pixels that contribute most to disclosure. Moreover, pixel perturbation is enforced incrementally and it is driven by the observed residual risk. Our framework is not tied to a specific pixel perturbation mechanism, and is versatile enough to support a wide variety of techniques, including blurring, pixelation, noise addition and pixel masking. Empirical results show that even with the simplest perturbation techniques, our approach significantly improves the privacy/utility trade-off compared to conventional and advanced state-of-the-art methods.
|