{"data":{"id":"613d7b4b-11fc-4830-9f3f-d496f8b08177","title":"Securing Locally Deployed LLM-RAG Assistants: A Cross-Model and Cross-Lingual Evaluation of Indirect Prompt Injection Defenses","summary":"This study evaluates indirect prompt injection against locally deployed RAG assistants, testing four attack families across five defense configurations (C1–C5) and four local LLMs on a synthetic corpus of 40 documents and 32 queries. In the Llama 3.1 8B experiment, conditional Attack Success Rate fell from 70.4% without defenses (C1) to 22.2% with deterministic post-generation filtering (C5). Context contamination remained the main residual weakness, and the authors note the filter and evaluator share some detection indicators, so post-filter ASR reflects unsafe content left in responses.","solution":"Deterministic post-generation filtering (C5), which the authors say supports independent security enforcement, reduced conditional ASR from 70.4% to 22.2% in the Llama 3.1 8B experiment and gave post-filter ASRs of 7.4–22.2% across the four models, with Answer Utility ranging from 21.9% to 62.5%.","labels":["security","research"],"sourceUrl":"https://doi.org/10.3390/app162111039","publishedAt":"2026-11-07T00:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection","data_extraction"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["Meta"],"affectedVendorsRaw":["Llama 3.1 8B"],"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":"2026-11-07T00:00:00.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["confidentiality","integrity","safety"],"aiComponentTargeted":"rag","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"peer_reviewed","atlasIds":["AML.T0051"]}}