AI Paper Atlas

Research map / Video / Video generation

Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation

Yeonghwan Song, Chanhui Lee, Jinsoo Park, Jeany Son

ECCV 2026 · Video › Video generation · approach: Compositional text-to-video diffusion · 0 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
Add text suppression loss L_sup to encoder attack (ablation)Anti-Prompt · CogVideoX white-boxVideo-LLM average (lower is stronger): 4.11 -> 3.92Improved
Add text suppression loss L_sup to encoder attack (ablation)Anti-Prompt · CogVideoX white-box VBenchSubject Consistency: 91.96 -> 92.94Mixed
Add visual dominance loss L_vis to encoder attack (ablation)Anti-Prompt · CogVideoX white-boxVideo-LLM average (lower is stronger): 4.11 -> 3.59Improved
Combine L_sup and L_vis (ablation)Anti-Prompt · CogVideoX white-boxVideo-LLM average (lower is stronger): 3.59 -> 3.25Improved
Use Anti-Prompt instead of I2VGuard (white-box)Anti-Prompt · CogVideoX VBenchI2V Subject: 94.58 -> 91.20Improved
Use Anti-Prompt instead of I2VGuard (white-box)Anti-Prompt · LTX-Video Video-LLM averageaverage: 3.28 -> 3.12Improved
Use Anti-Prompt under unseen promptsAnti-Prompt · CogVideoX Video-LLMaverage: 3.86 -> 2.99Improved
Transfer perturbation across architectures (LTX to CogVideoX)Anti-Prompt · black-boxVideo-LLM average: 4.47 -> 4.15Improved
Transfer from CogVideoX to LTX-VideoAnti-Prompt · black-box VBenchI2V Subject: 94.52 vs 94.61Mixed
Use losses on intermediate attention statistics instead of generating reference videoAnti-Prompt · CogVideoX-5B efficiencytotal PFLOPs: 54.25 -> 26.82Improved
Compare perturbation imperceptibility with I2VGuardAnti-Prompt · LTX-VideoDISTS: 0.130 -> 0.138Hurt
Compare perturbation imperceptibility with I2VGuardAnti-Prompt · CogVideoXPSNR: 32.86 -> 35.10Improved

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