AI RESEARCH
PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM Jailbreaking
arXiv CS.CV
•
ArXi:2507.21540v3 Announce Type: replace-cross The increasing sophistication of large vision-language models (LVLMs) has been accompanied by advances in safety alignment mechanisms designed to prevent harmful content generation. However, these defenses remain vulnerable to sophisticated adversarial attacks. Existing jailbreak methods typically rely on direct and semantically explicit prompts, overlooking subtle vulnerabilities in how LVLMs compose information over multiple reasoning steps.