Research map / Image generation / Editing and style transfer
DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editing
Tarik Can Ozden, Ozgur Kara, Oguzhan Akcin, Kerem Zaman, Shashank Srivastava, Sandeep P. Chinchali, James Matthew Rehg
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 L_noise imperceptibility loss (ablation) | DiffVax · Image immunization (unseen) | SSIM (Noise): 0.786 -> 0.989 | Improved |
| add L_noise imperceptibility loss (ablation) | DiffVax · Image immunization (unseen) | SSIM of edited image: 0.520 -> 0.526 | Mixed |
| add L_edit editing-failure loss (ablation) | DiffVax · Image immunization (unseen) | SSIM of edited image: 0.932 -> 0.526 | Improved |
| train a feed-forward immunizer instead of per-image optimization | DiffVax vs PhotoGuard-D · Image immunization | runtime per image (s): 911.60 -> 0.07 | Improved |
| DiffVax vs PhotoGuard-D on unseen SSIM | DiffVax · Image immunization (unseen) | SSIM of edited image: 0.523 -> 0.526 | Hurt |
| apply denoiser counter-attack | DiffVax vs PG-D · Image immunization (unseen) | SSIM of edited image: 0.709 -> 0.565 | Improved |
| apply JPEG 0.75 counter-attack | DiffVax vs PG-D · Image immunization (unseen) | SSIM of edited image: 0.674 -> 0.538 | Improved |
| apply IMPRESS counter-attack | DiffVax vs PG-D · Image immunization (unseen) | SSIM of edited image: 0.563 -> 0.500 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DiffusionGuard — DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing (ICLR 2025) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Distraction is All You Need: Memory-Efficient Image Immunization against Diffusion-Based Image Editing (CVPR 2024 · similarity 0.88)
- DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing (ICLR 2025 · similarity 0.88)
- Anti-Diffusion: Preventing Abuse of Modifications of Diffusion-Based Models (AAAI 2025 · similarity 0.87)
- Towards Efficient Diffusion-Based Image Editing with Instant Attention Masks (AAAI 2024 · similarity 0.84)
- TiNO-Edit: Timestep and Noise Optimization for Robust Diffusion-Based Image Editing (CVPR 2024 · similarity 0.84)
- Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models (CVPR 2025 · similarity 0.84)
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.
