{"data":{"id":"17931e30-7dc1-480b-a054-aa4fc67bc92b","title":"An Explainable Graph Attention Network for Indirect Prompt Injection Detection in RAG Systems","summary":"Researchers built a Graph Attention Network that flags malicious instructions hidden in documents retrieved for RAG systems, before those documents reach the language model. Each document is split into sentences encoded with a frozen DeBERTa-v3-base model, and a two-layer GAT with about 0.4 million trainable parameters classifies it as benign or malicious. On a 2,000-sample test set of financial and corporate policy documents, the model reached 99.80% accuracy and an F1-score of 0.998, though the authors say performance on unseen data remains to be established.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://doi.org/10.22214/ijraset.2026.85566","publishedAt":"2026-11-04T00:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"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":"2026-11-04T00:00:00.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"rag","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"peer_reviewed","atlasIds":["AML.T0051"]}}