FeatMark: Feature-level Watermark Protection against Mimicry Attacks with Diffusion Models
cs.CR, cs.CV
Submitted: 2026-09-25
Updated: 2026-09-25
Terminology
Sources
- Variational image compression with a scale hyperprior
- DiffEdit: Diffusion-based semantic image editing with mask guidance
- FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models
- WMCopier: Forging Invisible Image Watermarks on Arbitrary Images
- An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
- Prompt-to-Prompt Image Editing with Cross Attention Control
- Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI
- LoRA: Low-Rank Adaptation of Large Language Models
- Stable Signature is Unstable: Removing Image Watermark from Diffusion Models
- A Transfer Attack to Image Watermarks
- A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
- UnMarker: A Universal Attack on Defensive Image Watermarking
- Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples
- A Crack in the Bark: Leveraging Public Knowledge to Remove Tree-Ring Watermarks
- AudioMarkBench: Benchmarking Robustness of Audio Watermarking
- Decoupled Weight Decay Regularization
- Leveraging Optimization for Adaptive Attacks on Image Watermarks
- Diffusion Models for Adversarial Purification
- SAM 2: Segment Anything in Images and Videos
- Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs