RunawayEvil: Jailbreaking the Image-to-Video Generative Models

TL;DR

RunawayEvil introduces a novel self-evolving multimodal jailbreak framework that significantly enhances attack success rates on image-to-video models, highlighting critical security vulnerabilities in current systems.

Contribution

This paper presents the first adaptive, reinforcement learning-based multimodal jailbreak framework for I2V models, enabling continuous attack strategy evolution without human input.

Findings

Achieves state-of-the-art attack success rates on commercial I2V models.

Outperforms existing methods by 58.5 to 79 percent on COCO2017.

Demonstrates the effectiveness of self-evolving attack strategies.

Abstract

Image-to-Video (I2V) generation synthesizes dynamic visual content from image and text inputs, providing significant creative control. However, the security of such multimodal systems, particularly their vulnerability to jailbreak attacks, remains critically underexplored. To bridge this gap, we propose RunawayEvil, the first multimodal jailbreak framework for I2V models with dynamic evolutionary capability. Built on a "Strategy-Tactic-Action" paradigm, our framework exhibits self-amplifying attack through three core components: (1) Strategy-Aware Command Unit that enables the attack to self-evolve its strategies through reinforcement learning-driven strategy customization and LLM-based strategy exploration; (2) Multimodal Tactical Planning Unit that generates coordinated text jailbreak instructions and image tampering guidelines based on the selected strategies; (3) Tactical Action Unit that executes and evaluates the multimodal coordinated attacks. This self-evolving architecture allows the framework to continuously adapt and intensify its attack strategies without human intervention. Extensive experiments demonstrate RunawayEvil achieves state-of-the-art attack success rates on commercial I2V models, such as Open-Sora 2.0 and CogVideoX. Specifically, RunawayEvil outperforms existing methods by 58.5 to 79 percent on COCO2017. This work provides a critical tool for vulnerability analysis of I2V models, thereby laying a foundation for more robust video generation systems.