AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Jailbreaking on Text-to-Video Models via Scene Splitting Strategy

Wonjun Lee, Haon Park, Doehyeon Lee, Bumsub Ham, Suhyun Kim

ICLR 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: LLM jailbreak and injection defense

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 Scene Manipulation (iterative single-scene modification) to Scene Splitting (ablation)SceneSplit · T2VSafetyBench, Veo2ASR: 42.7% -> 60.9%Improved
add Strategy Update (outer loop plus Strategy Library) (ablation)SceneSplit · T2VSafetyBench, Veo2ASR: 60.9% -> 78.2%Improved
add Strategy Library with iterations held fixed (ablation)SceneSplit · T2VSafetyBench, Veo2ASR: 69.1% -> 78.2%Improved
split prompt into multiple scenes (Scene Division) alone (ablation)T2VSafetyBench prompts · one-shot ASR, Veo2 and HailuoASR: Veo2 33.1% -> 37.7%; Hailuo 40.9% -> 53.6%Improved
apply only paraphrasing to soften language, without scene division (ablation)T2VSafetyBench prompts · one-shot ASR, Veo2 and HailuoASR: Veo2 33.1% -> 30.0%; Hailuo 40.9% -> 42.7%Mixed
combine scene division with paraphrasing (ablation)Scene Division · one-shot ASR, Veo2 and HailuoASR: Veo2 37.7% -> 42.7%; Hailuo 53.6% -> 56.4%Improved
use Scene Manipulation instead of regenerating new scene splits each iteration (ablation)SceneSplit · Veo2, 5 iterations, no Strategy UpdateASR: 46.4% -> 60.9%Improved
increase outer iterations T from 1 to 3 (ablation)SceneSplit · Veo2ASR: 60.9% -> 73.6% -> 78.2%Improved
increase inner iterations I from 3 to 8 (ablation)SceneSplit · Veo2ASR: 57.7% -> 60.9% -> 62.4%Improved
add Strategy Update for efficiency (ablation)SceneSplit · Veo2average attack attempts: 6.22 -> 5.54 attempts, time 311.52s -> 323.06sImproved
raise strategy retrieval similarity threshold from 0.6 to 0.8 (ablation)SceneSplit · Veo2ASR: 78.2% -> 72.7%Hurt
use non-fixed initial scene split instead of fixed (ablation)SceneSplit · Veo2ASR: 78.2% -> 77.3%No clear effect

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