Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Dipesh Tamboli, Vineet Punyamoorty, Atharv Pawar, Vaneet Aggarwal

TL;DR

This work proposes a privacy-preserving pipeline that supports high-quality editing while keeping users in control over their biometric data in face-centric use cases, and offers both technical feasibility and normative guidance for protecting digital identity.

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.

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

TL;DR

This work proposes a privacy-preserving pipeline that supports high-quality editing while keeping users in control over their biometric data in face-centric use cases, and offers both technical feasibility and normative guidance for protecting digital identity.

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.
Paper Structure (28 sections, 13 equations, 2 figures, 3 tables, 1 algorithm)

This paper contains 28 sections, 13 equations, 2 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Rethinking Privacy in Generative Image Editing Pipelines
  3. Privacy Threat Model and Information-Theoretic Analysis
  4. Threat Model
  5. Explicit Facial Removal
  6. Biometric Privacy Definition
  7. Soft Attribute Leakage
  8. Cloud Editing and Local Reintegration
  9. Scope and Limitations
  10. Geometric Validity and Safe Editing Bounds
  11. Geometric Assumptions
  12. Failure Modes
  13. Ensuring Application Alignment
  14. Evaluation Setup and Baselines
  15. Visual Fidelity and Identity Preservation
  16. ...and 13 more sections

Figures (2)

  • Figure 1: Quantification of privacy gains.(A) Overview of our pipeline; (B) Conceptual depiction of privacy threat and masking; (C) Attribute classification performance on masked versus unmasked images, using Gemini, Grok, and LLaMA. Metrics include accuracy, precision, recall, and F1-score. Error bars denote standard deviation across models.
  • Figure 2: Qualitative comparison of privacy‐preserving face edits. Each row corresponds to a different input image (leftmost column), followed by three edited versions: “GPT (No Privacy)” (second column), “GPT (Reconstruction)” (third column), and our method (“Ours (Face Re‐integration)”, rightmost column). Beneath each image, we report Face‐FID (FID), Cosine similarity (COS), and CLIP score (CLIP) relative to the prompt “Convert this image into a professional studio headshot.”