Protective Perturbations Must Survive the Resize: Scale-Robust Image Immunization against Malicious Editing
cs.CV
Submitted: 2026-10-05
Updated: 2026-10-08
Comments: 10 pages, 6 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
- Mist: Towards Improved Adversarial Examples for Diffusion Models
- DeContext as Defense: Safe Image Editing in Diffusion Transformers
- Do Protective Perturbations Really Protect Portrait Privacy under Real-world Image Transformations?
- Qwen-Image Technical Report
- My Face Is Mine, Not Yours: Facial Protection Against Diffusion Model Face Swapping
- Towards Robust Protective Perturbation against DeepFake Face Swapping
- Towards Transferable Defense Against Malicious Image Edits
- Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle
- Purify Once, Edit Freely: Breaking Image Protections under Model Mismatch
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