When Recovery Matters: The Blind Spot of Surrogate Privacy in MLLM Editing
For researchers and practitioners in privacy-preserving multimodal editing, this work addresses a previously overlooked recovery problem with a new benchmark and methods.
The paper identifies a blind spot in surrogate-based privacy-preserving editing for MLLMs: the local recovery of the source image after editing is neglected. It introduces SPPE, a benchmark with 36 privacy categories and 65 instructions, and proposes methods ERMA for editability assessment (improving SRCC by 13.9% and PLCC by 12.3%) and C2E-S2SER for recovery (outperforming SOER on all 8 metrics).
Multimodal Large Language Models (MLLMs) enable flexible instruction-driven image editing, but privacy risks arise when user images expose diverse and user-specific private content. Canonical privacy protection strategies typically substitute sensitive regions with surrogate content before cloud editing. Yet, the resulting output is often an edited surrogate rather than the desired edited source image, neglecting the local recovery in both design and evaluation scope. To this end, we introduce SPPE (Surrogate-based Privacy-Preserving Editing), the first recovery-oriented benchmark covering 36 fine-grained privacy categories and 65 editing instructions. It defines two complementary tasks: 1) editability assessment, which estimates before cloud interaction whether a surrogate can induce an edit consistent with the original image; and 2) surrogate-to-source edit recovery, which evaluates whether the edited surrogate can be transferred back to the private source with the edit effect preserved. We address each task with a dedicated method: ERMA predicts surrogate editability through instruction-aware multimodal relation modeling, while \method performs cycle-consistent recovery by using the surrogate editing pair as visual edit evidence and the source image as a source-preserving anchor. Experiments on SPPE and InstructPix2Pix show consistent improvements on both tasks. For editability assessment, ERMA improves over the best-performing baselines by 13.9% in SRCC and 12.3% in PLCC. For surrogate-to-source edit recovery, C2E-S2SER outperforms SOER across all 8 source integrity and edit consistency metrics on SPPE.