Cross-Branch Conflict as a Shield: Safeguarding Facial Identities in Unified Multimodal Image Editing

תקציר מקורי באנגליתarXiv:2607.16898v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) have recently demonstrated powerful instruction-based image editing capabilities, but they also raise serious concerns about unauthorized manipulation of personal portraits. Existing adversarial protection methods are mainly designed for either visual understanding or image generation models and often become ineffective when transferred to UMMs, which process an image through multiple complementary visual pathways. In this work, we first conduct a feature-level analysis of unified image editing. We observe that the ViT-based understanding branch and the VAE-based generation branch exhibit non-trivial structural agreement for the same input image. Although perturbing an individual branch can reduce this agree