Saved in:
Bibliographic Details
Main Authors: Cheng, Zehua, Dai, Wei, Sun, Jiahao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.23584
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917437095542784
author Cheng, Zehua
Dai, Wei
Sun, Jiahao
author_facet Cheng, Zehua
Dai, Wei
Sun, Jiahao
contents Multi-modal retrieval-augmented generation (MRAG) systems retrieve visual evidence from large image corpora to ground the responses of large multi-modal models, yet the retrieved images frequently contain human faces whose identities constitute sensitive personal information. Existing anonymization techniques that destroy the non-identity visual cues that downstream reasoning depends on or fail to provide principled privacy guarantees. We propose Identity-Decoupled MRAG, a framework that interposes a generative anonymization module between retrieval and generation. Our approach consists of three components: (i)a disentangled variational encoder that factorizes each face into an identity code and a spatially-structured attribute code, regularized by a mutual-information penalty and a gradient-based independence term; (ii)a manifold-aware rejection sampler that replaces the identity code with a synthetic one guaranteed to be both distinct from the original and realistic; and (iii)a conditional latent diffusion generator that synthesizes the anonymized face from the replacement identity and the preserved attributes, distilled into a latent consistency model for low-latency deployment. Privacy is enforced through a multi-oracle ensemble of face recognition models with a hinge-based loss that halts optimization once identity similarity drops below the impostor-regime threshold.
format Preprint
id arxiv_https___arxiv_org_abs_2604_23584
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Identity-Decoupled Anonymization for Visual Evidence in Multi-modal Retrieval-Augmented Generation
Cheng, Zehua
Dai, Wei
Sun, Jiahao
Computer Vision and Pattern Recognition
Information Retrieval
Multi-modal retrieval-augmented generation (MRAG) systems retrieve visual evidence from large image corpora to ground the responses of large multi-modal models, yet the retrieved images frequently contain human faces whose identities constitute sensitive personal information. Existing anonymization techniques that destroy the non-identity visual cues that downstream reasoning depends on or fail to provide principled privacy guarantees. We propose Identity-Decoupled MRAG, a framework that interposes a generative anonymization module between retrieval and generation. Our approach consists of three components: (i)a disentangled variational encoder that factorizes each face into an identity code and a spatially-structured attribute code, regularized by a mutual-information penalty and a gradient-based independence term; (ii)a manifold-aware rejection sampler that replaces the identity code with a synthetic one guaranteed to be both distinct from the original and realistic; and (iii)a conditional latent diffusion generator that synthesizes the anonymized face from the replacement identity and the preserved attributes, distilled into a latent consistency model for low-latency deployment. Privacy is enforced through a multi-oracle ensemble of face recognition models with a hinge-based loss that halts optimization once identity similarity drops below the impostor-regime threshold.
title Identity-Decoupled Anonymization for Visual Evidence in Multi-modal Retrieval-Augmented Generation
topic Computer Vision and Pattern Recognition
Information Retrieval
url https://arxiv.org/abs/2604.23584