AI Paper Atlas

Research map / Video / Video generation

Anti-I2V: Safeguarding your Photos from Malicious Image-to-video Generation

Duc Vu, Anh Nguyen, Chi Tran, Anh Tran

CVPR 2026 · Video › Video generation · approach: Efficient video diffusion models · 4 citations (OpenAlex)

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 changedWhereMeasuredEffect
Perturb in Lab plus frequency space (DSP) instead of RGB (ablation)Anti-I2V · CelebV-Text subset, CogVideoX-5BQ-Align (video): 0.692 -> 0.610Improved
Use Lab space alone instead of RGB (ablation)Anti-I2V · CelebV-Text subset, CogVideoX-5BQ-Align (video): 0.692 -> 0.765Hurt
Add RGB space to DSP (ablation)Anti-I2V · CelebV-Text subset, CogVideoX-5BQ-Align (video): 0.610 -> 0.639Hurt
Add IRC loss to denoising loss (ablation)Anti-I2V · CelebV-Text subset, CogVideoX-5BISM: 0.582 -> 0.535Improved
Add targeted IRA on VAE to denoising loss (ablation)Anti-I2V · CelebV-Text subset, CogVideoX-5BISM: 0.582 -> 0.507Improved
Add targeted IRA on denoiser to denoising loss (ablation)Anti-I2V · CelebV-Text subset, CogVideoX-5BISM: 0.582 -> 0.493Improved
Use targeted instead of untargeted IRA on denoiser (ablation)Anti-I2V · CelebV-Text subset, CogVideoX-5BISM: 0.507 -> 0.493Improved
Add IRC to combined IRA losses (ablation)Anti-I2V · CelebV-Text subset, CogVideoX-5BISM: 0.484 -> 0.476Improved
Add auxiliary LPIPS and CLIP loss (ablation)Anti-I2V · CelebV-Text subset, CogVideoX-5BISM: 0.476 -> 0.462Improved
Raise Lab budget from 16/255 to 32/255 (ablation)Anti-I2V · CelebV-Text subset, CogVideoX-5BQ-Align (video): 0.562 -> 0.588Hurt
Lower Lab budget from 16/255 to 8/255 (ablation)Anti-I2V · CelebV-Text subset, CogVideoX-5BQ-Align (video): 0.562 -> 0.567Hurt
Apply IRC to last 3 layers instead of all layers after 27th (ablation)Anti-I2V · CelebV-Text subset, CogVideoX-5BISM: 0.458 -> 0.462No clear effect

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy