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

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.

• Publication year

  2026

• Venue

  Unknown venue

• Publication date

  2026-03-03

• Fields of study

  Computer Science

• Identifiers
  arXiv 2603.03412
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Discrete State Diffusion Models: A Sample Complexity Perspective

  2025cited by this paper
• Fairness & Privacy in an Age of Generative AI

  2024cited by this paper
• Generative AI model privacy: a survey

  2024cited by this paper
• Privacy and Security Concerns in Generative AI: A Comprehensive Survey

  2024cited by this paper
• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

  2024cited by this paper
• Fast and robust virtual try-on based on parser-free generative adversarial network

  2024cited by this paper
• Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing

  2024cited by this paper
• LLaMA: Open and Efficient Foundation Language Models

  2023cited by this paper
• A Flow-based Generative Network for Photo-Realistic Virtual Try-On

  2022cited by this paper
• Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding

  2022cited by this paper
• Towards Robust Blind Face Restoration with Codebook Lookup Transformer

  2022cited by this paper
• Person Image Synthesis via Denoising Diffusion Model

  2022cited by this paper
• GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

  2021cited by this paper
• Generative Adversarial Networks

  2021cited by this paper
• Learning Transferable Visual Models From Natural Language Supervision

  2021cited by this paper
• Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-On

  2021cited by this paper
• FICGAN: Facial Identity Controllable GAN for De-identification

  2021cited by this paper
• High-Resolution Image Synthesis with Latent Diffusion Models

  2021cited by this paper
• Score-Based Generative Modeling through Stochastic Differential Equations

  2020cited by this paper
• Denoising Diffusion Probabilistic Models

  2020cited by this paper
• MediaPipe: A Framework for Building Perception Pipelines

  2019cited by this paper
• GENERATIVE ADVERSARIAL NETS

  2018cited by this paper
• Siamese Generative Adversarial Privatizer for Biometric Data

  2018cited by this paper
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

  2017cited by this paper
• Deep Learning Face Attributes in the Wild

  2014cited by this paper
• Poisson image editing

  2003cited by this paper
• Equivalence and efficiency of image alignment algorithms

  2001cited by this paper

• No citing papers are available for this paper.