{"data":{"id":"d670863e-c7cb-4060-afb5-cf16f39531e7","title":"MPIDetector: Detecting Multi-modal Prompt Injection via LLM-based Reasoning","summary":"MPIDetector is a detection framework for multi-modal prompt injection that uses few-shot in-context learning on LLMs, with no fine-tuning, and reasoning over specific prompt templates and attack examples. The authors evaluated it on eight textual and seven visual malicious categories plus benign data, across Gemini-2.0-Flash, Qwen3-VL-32B-Instruct and Doubao-seed-1.6-flash. It reached up to 90.91% accuracy and 100% recall on text, up to 99.28% accuracy with 100% precision on visual inputs, and up to 99.80% detection on 500 obfuscated WebInject web-agent injections.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.30202v1","publishedAt":"2026-10-21T10:27:56.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["Google"],"affectedVendorsRaw":["Gemini-2.0-Flash","Qwen3-VL-32B-Instruct","Doubao-seed-1.6-flash"],"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":"2026-10-21T10:27:56.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0051"]}}