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

arXiv:2607.16898 · cs.CV, cs.CL, cs.CR · Submitted 2026-07-18 · Read on arXiv

Weiwei Tan, Junxian Li, Rui Wang, Zhenhua Xu, Yanjun Zhang, Yu Leo Zhang

cs.CV, cs.CL, cs.CR

Submitted: 2026-07-18

Comments: 14 pages, preprint

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Adversarial Examples — 12× in this paper · explained in 2 episodes
• Consistency — 12× in this paper · explained in 3 episodes
• Alignment — 9× in this paper · explained in 1 episode
• Diffusion Model — 9× in this paper · explained in 8 episodes
• Diffusion Models — 9× in this paper · explained in 6 episodes
• Thinking mode — 5× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Ablation study — 3× in this paper · explained in 1 episode
• Centered Kernel Alignment — 3× in this paper
• Cooperation — 3× in this paper · explained in 2 episodes
• Latent Space — 3× in this paper · explained in 7 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Transferability — 3× in this paper · explained in 4 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Adversarial Attacks — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Symposium on Security and Privacy — 2× in this paper
• Trace — 2× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Identity Similarity Metric — 1× in this paper
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Multimodal Fusion — 1× in this paper · explained in 3 episodes
• Nash Equilibrium — 1× in this paper · explained in 2 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Variational Bayes — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
• Emerging Properties in Unified Multimodal Pretraining
• SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Explaining and Harnessing Adversarial Examples
• CLIPScore: A Reference-free Evaluation Metric for Image Captioning
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Denoising Diffusion Probabilistic Models
• HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Auto-Encoding Variational Bayes
• G squared TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models
• ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area
• Mist: Towards Improved Adversarial Examples for Diffusion Models
• Visual Instruction Tuning
• I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing
• VEAttack: Downstream-agnostic Vision Encoder Attack against Large Vision Language Models
• Raising the Cost of Malicious AI-Powered Image Editing
• Intriguing properties of neural networks
• InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models