Cross-Branch Conflict as a Shield: Safeguarding Facial Identities in Unified Multimodal Image Editing
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-bas
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%Tongyi-MAI/Z-Image-Turbo →
“Fuzzy title match (0.73): “Cross-Branch Conflict as a Shield: Safeguarding Facial Ident” ≈ “Tongyi-MAI/Z-Image-Turbo””
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- LinkedLinked via arxiv author · 85%Weiwei Tan →
“Cross-Branch Conflict as a Shield: Safeguarding Facial Identities in Unified Multimodal Image Editing”
- LinkedLinked via arxiv author · 85%Junxian Li →
“Cross-Branch Conflict as a Shield: Safeguarding Facial Identities in Unified Multimodal Image Editing”
- LinkedLinked via arxiv author · 85%Qirui Wang →
“Cross-Branch Conflict as a Shield: Safeguarding Facial Identities in Unified Multimodal Image Editing”
- LinkedLinked via arxiv author · 85%Zhenhua Xu →
“Cross-Branch Conflict as a Shield: Safeguarding Facial Identities in Unified Multimodal Image Editing”
- LinkedLinked via arxiv author · 85%Yanjun Zhang →
“Cross-Branch Conflict as a Shield: Safeguarding Facial Identities in Unified Multimodal Image Editing”