{"data":{"id":"e18e8a00-8513-4ec0-8143-142bb5865278","title":"What Survives the Shift from Text to Pixels? Conditional Protection against Prompt Injection in Image-Rendered Documents","summary":"This study compares text and page-image versions of 191 English question-answering sources across six multimodal models to test indirect prompt injection. Rendering untrusted content as images reduces marker appending and answer formatting for every model, but Qwen3-VL-8B still executes image-borne answer replacement at 77.96%. Protection varies by target type, rendering settings, wording, and repetition, and Qwen falls to 61.99% utility when answers combine two evidence spans.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.24231v1","publishedAt":"2026-11-18T11:08:07.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Qwen3-VL-8B","Gemini","GPT-5-nano"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-11-18T11:08:07.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"api","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0051"]}}