Research map / Image generation / Editing and style transfer
Toward Transferable Defense Against Malicious Image Edits
Jie Zhang, Shuai Dong, Shiguang Shan, Chen Xilin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add TDAE to SA | SA · INS intra-model | LPIPS: 0.3966 -> 0.4396 | Improved |
| add FDM to PGE | PGE · INS intra-model | LPIPS: 0.3801 to 0.3982 | Improved |
| add TDAE to PGD | PGD · SD3 intra-model | LPIPS: 0.3921 to 0.4109 | Improved |
| add TDAE to PGD | PGD · SD14 intra-model | LPIPS: 0.4989 vs. 0.5504 | Improved |
| add TDAE to PGD (transfer INS to SD14) | PGD · INS->SD14 cross-model | LPIPS: 0.4658 to 0.4930 | Improved |
| add TDAE to SA (transfer SD3 to INS) | SA · SD3->INS cross-model | LPIPS: 0.3457 to 0.3673 | Improved |
| add TDAE to SA (transfer SD14 to SD3) | SA · SD14->SD3 cross-model | LPIPS: 0.3634 to 0.3789 | Improved |
| add FDM to PGD (ablation) | PGD · INS intra-model | LPIPS: 0.3157 -> 0.3429 | Improved |
| add DPD to PGD (ablation) | PGD · INS intra-model | LPIPS: 0.3157 -> 0.3694 | Improved |
| add DPD to PGD+FDM (full TDAE) (ablation) | PGD + FDM · INS intra-model | LPIPS: 0.3429 -> 0.3801 | Improved |
| add FDM to SA (ablation) | SA · INS->SD3 cross-model | PSNR: 20.98 -> 20.03 | Improved |
| replace TPA with FDM on SA | SA · INS intra-model | time per iteration (s): 71.37 -> 6.49 | Improved |
Closest papers by meaning
- Distraction is All You Need: Memory-Efficient Image Immunization against Diffusion-Based Image Editing (CVPR 2024 · similarity 0.91)
- DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing (ICLR 2025 · similarity 0.90)
- Pixel Is Not a Barrier: An Effective Evasion Attack for Pixel-Domain Diffusion Models (AAAI 2025 · similarity 0.89)
- AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption (ICLR 2025 · similarity 0.88)
- BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing (NeurIPS 2025 · similarity 0.87)
- Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
