PRIVATEEDIT: A Privacy-Preserving Pipeline for Face-Centric Generative Image Editing

2026-03-03

AI Summary

This work addresses the privacy and authorization risks associated with uploading users’ facial biometric data to third-party generative models for image editing. We propose an on-device privacy-preserving solution that leverages local image segmentation and dynamic facial masking to decouple identity-sensitive regions from editable content. Without modifying or retraining the third-party model, our approach enables user-controlled, high-fidelity editing. The system employs a privacy-by-design architecture and an interactive anonymization interface, allowing users to adjust the trade-off between privacy and output quality based on their trust level, while remaining compatible with commercial APIs. We validate the effectiveness of our method in professional avatar generation scenarios, demonstrating strong privacy guarantees without compromising edit quality. The implementation is open-sourced to advance privacy-first practices in generative AI.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Privacy
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Recent advances in generative image editing have enabled transformative applications, from professional head shot generation to avatar stylization. However, these systems often require uploading high-fidelity facial images to third-party models, raising concerns around biometric privacy, data misuse, and user consent. We propose a privacy-preserving pipeline that supports high-quality editing while keeping users in control over their biometric data in face-centric use cases. Our approach separates identity-sensitive regions from editable image context using on-device segmentation and masking, enabling secure, user-controlled editing without modifying third-party generative models. Unlike traditional cloud-based tools, PRIVATEEDIT enforces privacy by default: biometric data is never exposed or transmitted. This design requires no access to or retraining of third-party models, making it compatible with a wide range of commercial APIs. By treating privacy as a core design constraint, our system supports responsible generative AI centered on user autonomy and trust. The pipeline includes a tunable masking mechanism that lets users control how much facial information is concealed, allowing them to balance privacy and output fidelity based on trust level or use case. We demonstrate its applicability in professional and creative workflows and provide a user interface for selective anonymization. By advocating privacy-by-design in generative AI, our work offers both technical feasibility and normative guidance for protecting digital identity. The source code is available at https://github.com/Dipeshtamboli/PrivateEdit-Privacy-Preserving-GenAI.

Problem

• privacy-preserving
• generative image editing
• biometric privacy
• face-centric
• user consent

Innovation

• privacy-preserving
• generative image editing
• on-device segmentation
• biometric privacy
• masking mechanism