# When Privacy Meets Recovery: The Overlooked Half of Surrogate-Driven Privacy Preservation for MLLM Editing

arXiv: https://arxiv.org/abs/2512.07166 · HTML: https://mlsanity.com/paper/2512.07166/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 8 Dec 2025.

## Builds on (most cited first, 13 of 13)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Generating Images with Multimodal Language Models](https://mlsanity.com/paper/2305.17216/) (2023)
- [Making LLaMA SEE and Draw with SEED Tokenizer](https://mlsanity.com/paper/2310.01218/) (2023)
- [Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images](https://mlsanity.com/paper/1703.10660/) (2017)
- [Live Face De-Identification in Video](https://mlsanity.com/paper/1911.08348/) (2019)
- [Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Images](https://mlsanity.com/paper/1712.01066/) (2017)
- [Edit Transfer: Learning Image Editing via Vision In-Context Relations](https://mlsanity.com/paper/2503.13327/) (2025)
- [Realistic Full-Body Anonymization with Surface-Guided GANs](https://mlsanity.com/paper/2201.02193/) (2022)
- [Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection](https://mlsanity.com/paper/2307.06422/) (2023)
- [ReVision: A Dataset and Baseline VLM for Privacy-Preserving Task-Oriented Visual Instruction Rewriting](https://mlsanity.com/paper/2502.14780/) (2025)
- [Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models](https://mlsanity.com/paper/2506.07077/) (2025)

## Built on by (most cited first, 1 of 1)

- [When Recovery Matters: The Blind Spot of Surrogate Privacy in MLLM Editing](https://mlsanity.com/paper/2606.07171/) (2026)

## Abstract (arXiv)

Privacy leakage in Multimodal Large Language Models (MLLMs) has long been an intractable problem. Existing studies, though effectively obscure private information in MLLMs, often overlook the evaluation of the authenticity and recovery quality of user privacy. To this end, this work uniquely focuses on the critical challenge of how to restore surrogate-driven protected data in diverse MLLM scenarios. We first bridge this research gap by contributing the SPPE (Surrogate Privacy Protected Editable) dataset, which includes a wide range of privacy categories and user instructions to simulate real MLLM applications. This dataset offers protected surrogates alongside their various MLLM-edited versions, thus enabling the direct assessment of privacy recovery quality. By formulating privacy recovery as a guided generation task conditioned on complementary multimodal signals, we further introduce a unified approach that reliably reconstructs private content while preserving the fidelity of MLLM-generated edits. The experiments on both SPPE and InstructPix2Pix further show that our approach generalizes well across diverse visual content and editing tasks, achieving a strong balance between privacy protection and MLLM usability.